CreativeClawCo/creative-claw-marketplace

"name": "Creative Claw Co."       },       "repository": "https://github.com/CreativeClawCo/creative-claw-marketplace",

},       "repository": "https://github.com/CreativeClawCo/creative-claw-marketplace",       "homepage": "https://creativeclaw.co",

"repository": "https://github.com/CreativeClawCo/creative-claw-marketplace",

"homepage": "https://creativeclaw.co",

"name": "Creative Claw Co.",     "email": "support@creativeclaw.co",     "url": "https://creativeclaw.co"

"email": "support@creativeclaw.co",     "url": "https://creativeclaw.co"   },

"url": "https://creativeclaw.co"

},   "homepage": "https://creativeclaw.co",   "icon": "./.claude-plugin/icon.png",

"homepage": "https://creativeclaw.co",

"icon": "./.claude-plugin/icon.png",   "documentationUrl": "https://creativeclaw.co/how-to-connect/",   "supportUrl": "https://creativeclaw.co/help",

"documentationUrl": "https://creativeclaw.co/how-to-connect/",

"supportUrl": "https://creativeclaw.co/help",

"privacyPolicyUrl": "https://creativeclaw.co/privacy",

"termsOfServiceUrl": "https://creativeclaw.co/terms",

"repository": "https://github.com/CreativeClawCo/creative-claw-marketplace",

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

- [Cartesia TTS bytes API](https://docs.cartesia.ai/api-reference/tts/bytes)

- [Cartesia voice controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion)

- [Cartesia SSML guidance](https://docs.cartesia.ai/build-with-cartesia/capability-guides/ssml-tags)

Get model params first. Match the returned voice catalog's language, accent and delivery labels; use the exact voice_id. Verified public IDs from [Cartesia's voice library](https://play.cartesia.ai/voices) can also be used. Do not apply an 

Sources: current Creative Claw schema and [Cartesia delivery controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion).

"text": "I thought we had more time. <sigh> But the doors are already closing.",   "extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",

"extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",     "exaggeration": 0.35,

"audio_url": "https://cdn.example.com/authorized-reference.wav",

> I own this recording or have permission to use it, and this is my voice or I have the speaker's explicit permission to clone it and generate speech in this workspace. I authorize Creative Claw and the supported voice providers I select th

Recording guidance: [ElevenLabs instant cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning).

- [ElevenLabs models](https://elevenlabs.io/docs/overview/models)

- [Speech API contract](https://elevenlabs.io/docs/api-reference/text-to-speech/convert)

- [Speech prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [Instant Voice Cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning)

Sources: current Creative Claw model schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices). Voice browsing: [ElevenLabs Voice Library](https://elevenlabs.io/app/voice-library).

Find voices with get_model_params for this model, matching native language/accent and delivery labels before selecting the exact voice_id. The default English voice is not a universal language recommendation. Public [ElevenLabs Voice Librar

Sources: current Creative Claw schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices).

- [ElevenLabs v4 overview](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4)

- [ElevenLabs speech prompting practices](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [ElevenLabs text to dialogue API](https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert-with-timestamps)

References: https://docs.fish.audio/features/text-to-speech/drama-3 https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech

`get_model_params` contains 40 curated public voices with delivery descriptions and preview links. Set `include_voice_catalog: true` for a longer selection. Browse [HeyGen voices](https://creativeclaw.co/voices/heygen/) or read the [agent c

[HeyGen stock speech guidance](https://developers.heygen.com/docs/voices/speech), [instant clone speech controls](https://developers.heygen.com/docs/voices/heygen-voice-speech).

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw image, Character and voice tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

- [Cartesia TTS bytes API](https://docs.cartesia.ai/api-reference/tts/bytes)

- [Cartesia voice controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion)

- [Cartesia SSML guidance](https://docs.cartesia.ai/build-with-cartesia/capability-guides/ssml-tags)

Get model params first. Match the returned voice catalog's language, accent and delivery labels; use the exact voice_id. Verified public IDs from [Cartesia's voice library](https://play.cartesia.ai/voices) can also be used. Do not apply an 

Sources: current Creative Claw schema and [Cartesia delivery controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion).

"text": "I thought we had more time. <sigh> But the doors are already closing.",   "extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",

"extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",     "exaggeration": 0.35,

"audio_url": "https://cdn.example.com/authorized-reference.wav",

> I own this recording or have permission to use it, and this is my voice or I have the speaker's explicit permission to clone it and generate speech in this workspace. I authorize Creative Claw and the supported voice providers I select th

Recording guidance: [ElevenLabs instant cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning).

- [ElevenLabs models](https://elevenlabs.io/docs/overview/models)

- [Speech API contract](https://elevenlabs.io/docs/api-reference/text-to-speech/convert)

- [Speech prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [Instant Voice Cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning)

Sources: current Creative Claw model schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices). Voice browsing: [ElevenLabs Voice Library](https://elevenlabs.io/app/voice-library).

Find voices with get_model_params for this model, matching native language/accent and delivery labels before selecting the exact voice_id. The default English voice is not a universal language recommendation. Public [ElevenLabs Voice Librar

Sources: current Creative Claw schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices).

- [ElevenLabs v4 overview](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4)

- [ElevenLabs speech prompting practices](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [ElevenLabs text to dialogue API](https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert-with-timestamps)

References: https://docs.fish.audio/features/text-to-speech/drama-3 https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech

`get_model_params` contains 40 curated public voices with delivery descriptions and preview links. Set `include_voice_catalog: true` for a longer selection. Browse [HeyGen voices](https://creativeclaw.co/voices/heygen/) or read the [agent c

[HeyGen stock speech guidance](https://developers.heygen.com/docs/voices/speech), [instant clone speech controls](https://developers.heygen.com/docs/voices/heygen-voice-speech).

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw transcription, media editing, and assets"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{   "video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

"video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

- [browser-use/video-use](https://github.com/browser-use/video-use/blob/main/SKILL.md): retain source word timing; inspect audio gaps and output boundaries; preserve breaths/reactions; use short fades for discontinuous audio. Reopening enco

- [whitetowerai/cut-as-code video-to-shorts](https://github.com/whitetowerai/cut-as-code/blob/main/skills/video-to-shorts/SKILL.md): separate highlight selection from rendering; evaluate hook, completeness, audience relevance and editabilit

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{   "video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

"video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Read when selecting or prompting `music/mureka-v9.5`. This reference adapts Skywork's [Mureka music-maker skill](https://github.com/SkyworkAI/Skywork-Skills/blob/main/skywork-music-maker/SKILL.md) and [prompt guide](https://github.com/Skywo

- [ElevenLabs Music v2.5 announcement](https://elevenlabs.io/blog/music-v2-5-model)

- [ElevenLabs music best practices](https://elevenlabs.io/docs/overview/capabilities/music/best-practices)

- [ElevenLabs Music overview](https://elevenlabs.io/docs/eleven-creative/products/music)

- [ElevenLabs compose API](https://elevenlabs.io/docs/api-reference/music/compose)

- [ElevenLabs music quickstart and content restrictions](https://elevenlabs.io/docs/eleven-api/guides/cookbooks/music)

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

- [ElevenLabs Sound Effects overview and prompting guide](https://elevenlabs.io/docs/overview/capabilities/sound-effects)

- [ElevenLabs Sound Effects product guide](https://elevenlabs.io/docs/eleven-creative/playground/sound-effects)

- [ElevenLabs sound-effect API reference](https://elevenlabs.io/docs/api-reference/text-to-sound-effects/convert)

- [Official ElevenLabs sound-effects skill](https://github.com/elevenlabs/skills/blob/main/sound-effects/SKILL.md)

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

- [Cartesia TTS bytes API](https://docs.cartesia.ai/api-reference/tts/bytes)

- [Cartesia voice controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion)

- [Cartesia SSML guidance](https://docs.cartesia.ai/build-with-cartesia/capability-guides/ssml-tags)

Get model params first. Match the returned voice catalog's language, accent and delivery labels; use the exact voice_id. Verified public IDs from [Cartesia's voice library](https://play.cartesia.ai/voices) can also be used. Do not apply an 

Sources: current Creative Claw schema and [Cartesia delivery controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion).

"text": "I thought we had more time. <sigh> But the doors are already closing.",   "extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",

"extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",     "exaggeration": 0.35,

"audio_url": "https://cdn.example.com/authorized-reference.wav",

> I own this recording or have permission to use it, and this is my voice or I have the speaker's explicit permission to clone it and generate speech in this workspace. I authorize Creative Claw and the supported voice providers I select th

Recording guidance: [ElevenLabs instant cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning).

- [ElevenLabs models](https://elevenlabs.io/docs/overview/models)

- [Speech API contract](https://elevenlabs.io/docs/api-reference/text-to-speech/convert)

- [Speech prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [Instant Voice Cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning)

Sources: current Creative Claw model schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices). Voice browsing: [ElevenLabs Voice Library](https://elevenlabs.io/app/voice-library).

Find voices with get_model_params for this model, matching native language/accent and delivery labels before selecting the exact voice_id. The default English voice is not a universal language recommendation. Public [ElevenLabs Voice Librar

Sources: current Creative Claw schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices).

- [ElevenLabs v4 overview](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4)

- [ElevenLabs speech prompting practices](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [ElevenLabs text to dialogue API](https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert-with-timestamps)

References: https://docs.fish.audio/features/text-to-speech/drama-3 https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech

`get_model_params` contains 40 curated public voices with delivery descriptions and preview links. Set `include_voice_catalog: true` for a longer selection. Browse [HeyGen voices](https://creativeclaw.co/voices/heygen/) or read the [agent c

[HeyGen stock speech guidance](https://developers.heygen.com/docs/voices/speech), [instant clone speech controls](https://developers.heygen.com/docs/voices/heygen-voice-speech).

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

<meta name="viewport" content="width=640,height=360">   <title>Seekable WebGL orbit — four seconds</title>   <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>

<title>Seekable WebGL orbit — four seconds</title>   <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>   <style>

<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>

<!doctype html> <html><head>   <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>

<html><head>   <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>   <style>

<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>

<video id="footage" src="https://YOUR_ASSET_HOST/source.mp4"

data-start="0" data-duration="8" muted playsinline></video> <audio id="source-audio" src="https://YOUR_ASSET_HOST/source.mp4"   data-start="0" data-duration="8" data-volume="1"></audio>

<audio id="source-audio" src="https://YOUR_ASSET_HOST/source.mp4"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw image, video, voice, Character and theme tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

{   "notes": "Audience, tone, visual direction, do/don't guidance in Markdown.",   "referenceImageUrl": "https://...",

"notes": "Audience, tone, visual direction, do/don't guidance in Markdown.",   "referenceImageUrl": "https://...",   "fonts": [

"referenceImageUrl": "https://...",

"files": [         {           "url": "https://.../acme-regular.woff2",

{           "url": "https://.../acme-regular.woff2",           "weight": 400,

"url": "https://.../acme-regular.woff2",

{       "name": "Primary mark",       "url": "https://.../logo.svg",

"name": "Primary mark",       "url": "https://.../logo.svg",       "variant": "color",

"url": "https://.../logo.svg",

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

**Not connected yet?** If no Creative Claw tools (such as `list_models` or `generate_image`) are available, the plugin is installed but the server is not connected. Stop and give the user the click path: open the [Creative Claw plugin page]

description: "Creative Claw media, asset, Character, Film, and feedback tools"       transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt"

transport: "streamable_http"       url: "https://app.creativeclaw.co/mcp/chatgpt" policy:

url: "https://app.creativeclaw.co/mcp/chatgpt"

{   "video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

"video_url": "https://YOUR_CREATIVE_CLAW_CDN/source.mp4",

Official [Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare), [Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst), and [image prompting guidance](https://developers.openai.com/api/docs/gui

[Official model](https://ai.google.dev/gemini-api/docs/models/gemini-nano-banana-2.1), [prompting guide](https://ai.google.dev/gemini-api/docs/image-generation), [pricing](https://ai.google.dev/gemini-api/docs/pricing).

{"video_url":"https://example.com/master.mp4","overlays":[{"image_url":"https://example.com/logo.png","position":"bottom_right","width_percent":12,"margin_px":48}]}

{"clips":[{"type":"image","url":"https://example.com/title.png","duration_seconds":3},{"type":"video","url":"https://example.com/scene.mp4","include_audio":false},{"type":"image","url":"https://example.com/end.png","duration_seconds":4}],"a

- Creative Claw must be connected. If core tools such as `search_assets`, `get_theme`, `list_models`, or `generate_image` are missing, the plugin is installed but not connected: tell the user to open the plugin's Connectors tab in their app

Spoken languages (checked 2026-10-11, direct HeyGen Lipsync, Precision default mode): supplied audio drives mouth movements on an existing video. This endpoint does not generate or translate speech. Prepare correct finished speech in the ta

"params": {     "video_urls": [       "https://your-cdn.example/speaker.mp4"

"video_urls": [       "https://your-cdn.example/speaker.mp4"     ],

"https://your-cdn.example/speaker.mp4"

],     "audio_urls": [       "https://your-cdn.example/finished-speech.wav"

"audio_urls": [       "https://your-cdn.example/finished-speech.wav"     ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

"prompt": "Sync this video to the supplied finished speech.",   "video_urls": [     "https://your-cdn.example/speaker.mp4"

"video_urls": [     "https://your-cdn.example/speaker.mp4"   ],

"https://your-cdn.example/speaker.mp4"

],   "audio_urls": [     "https://your-cdn.example/finished-speech.wav"

"audio_urls": [     "https://your-cdn.example/finished-speech.wav"   ],

"https://your-cdn.example/finished-speech.wav"

Provider documentation checked 2026-10-11: https://developers.heygen.com/reference/create-lipsync, https://developers.heygen.com/lipsync-speed, https://developers.heygen.com/lipsync-precision.

Kling's official guidance favors specific visible details, named reference roles, chronological beats and a separate audio direction. Use positive descriptions. Keep necessary exclusions such as no subtitles or no background music in the pr

For storyboard sheets, identify the panels as shot-planning references and ask for finished full-frame footage. A storyboard grid or its annotations should not become the rendered scene. For video reference work, choose footage whose pacing

The Kling website's Keyframes workspace has controls that this integration does not expose. Here, middle frames are ordered references with no numeric per-frame timestamp field. Describe intended beat timing in the prompt; do not invent `at

"resolution": "720p",   "aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],

"aspect_ratio": "9:16",   "image_urls": ["https://example.com/imported-copper-bottle.png"],   "prompt": "@Image1 defines the copper bottle: retain its silhouette, cap, brushed finish and label placement. A single uninterrupted tabletop shot

"image_urls": ["https://example.com/imported-copper-bottle.png"],

"duration": "8",   "resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],

"resolution": "720p",   "video_urls": ["https://example.com/imported-source.mp4"],   "extras": { "video_mode": "edit" },

"video_urls": ["https://example.com/imported-source.mp4"],

The website's advertised resolution, default duration, voice-upload and timeline controls do not override this route's schema. [Operation specification](https://dev.pika.art/llms/kling/kling-4.0/omni-video)

Checked October 24, 2026. Prompting principles and model-level distinctions: [Kling 4 user guide](https://kling.ai/quickstart/kling-4-model-user-guide), especially effective prompts, reference roles, editing, audio and keyframes; [Kling 4 o

| H3 Max Recast and Kling Motion Control Pro | Preserve the source video soundtrack, or remove it where supported. This does not establish native generated-speech or translation support; the recorded language comes from the source. | | Seed

| Seedance 2.5 | English and Chinese, plus other documented languages including Spanish, Japanese and Arabic. Get the complete version-specific list from `get_model_params`; do not assume all Seedance versions share it. | | Kling 4.0 Omni (

| Kling 4.0 Omni (checked 2026-10-23) | Native dialogue is documented in English, Chinese and additional languages. Get the full version-specific list from `get_model_params({ model: "video/kling-4.0-omni" })`. Other languages, including He

| FLUX 3 Max (checked 2026-10-20) | Native audio is documented and fal demonstrates English dialogue. No verified per-language reliability list is published for these exact endpoints. Language-specific reliability remains unverified. Read `

Primary sources: [MiniMax H3 dialogue languages](https://github.com/MiniMax-AI/MiniMax-H3/blob/main/README.md), [H3 Max's relationship to H3](https://fal.ai/learn/devs/introducing-h3-max-by-fal), [Seedance 2.5 languages](https://docs.volcen

- [Cartesia TTS bytes API](https://docs.cartesia.ai/api-reference/tts/bytes)

- [Cartesia voice controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion)

- [Cartesia SSML guidance](https://docs.cartesia.ai/build-with-cartesia/capability-guides/ssml-tags)

Get model params first. Match the returned voice catalog's language, accent and delivery labels; use the exact voice_id. Verified public IDs from [Cartesia's voice library](https://play.cartesia.ai/voices) can also be used. Do not apply an 

Sources: current Creative Claw schema and [Cartesia delivery controls](https://docs.cartesia.ai/build-with-cartesia/capability-guides/volume-speed-emotion).

"text": "I thought we had more time. <sigh> But the doors are already closing.",   "extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",

"extras": {     "audio_url": "https://cdn.example.com/authorized-reference.wav",     "exaggeration": 0.35,

"audio_url": "https://cdn.example.com/authorized-reference.wav",

> I own this recording or have permission to use it, and this is my voice or I have the speaker's explicit permission to clone it and generate speech in this workspace. I authorize Creative Claw and the supported voice providers I select th

Recording guidance: [ElevenLabs instant cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning).

- [ElevenLabs models](https://elevenlabs.io/docs/overview/models)

- [Speech API contract](https://elevenlabs.io/docs/api-reference/text-to-speech/convert)

- [Speech prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [Instant Voice Cloning](https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning)

Sources: current Creative Claw model schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices). Voice browsing: [ElevenLabs Voice Library](https://elevenlabs.io/app/voice-library).

Find voices with get_model_params for this model, matching native language/accent and delivery labels before selecting the exact voice_id. The default English voice is not a universal language recommendation. Public [ElevenLabs Voice Librar

Sources: current Creative Claw schema and [ElevenLabs prompting](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices).

- [ElevenLabs v4 overview](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/eleven-v4)

- [ElevenLabs speech prompting practices](https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices)

- [ElevenLabs text to dialogue API](https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert-with-timestamps)

References: https://docs.fish.audio/features/text-to-speech/drama-3 https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech

`get_model_params` contains 40 curated public voices with delivery descriptions and preview links. Set `include_voice_catalog: true` for a longer selection. Browse [HeyGen voices](https://creativeclaw.co/voices/heygen/) or read the [agent c

[HeyGen stock speech guidance](https://developers.heygen.com/docs/voices/speech), [instant clone speech controls](https://developers.heygen.com/docs/voices/heygen-voice-speech).

1. Open the [Creative Claw plugin page](https://claude.ai/customize/plugins/id/3b9e3067-1092-46a5-b613-f52ddf9476ca%40anthropic-plugin-directory/connectors) in Claude (or Customize, then Plugins, then Creative Claw).

{   "notes": "Audience, tone, visual direction, do/don't guidance in Markdown.",   "referenceImageUrl": "https://...",

"notes": "Audience, tone, visual direction, do/don't guidance in Markdown.",   "referenceImageUrl": "https://...",   "fonts": [

"referenceImageUrl": "https://...",

"files": [         {           "url": "https://.../acme-regular.woff2",

{           "url": "https://.../acme-regular.woff2",           "weight": 400,

"url": "https://.../acme-regular.woff2",

{       "name": "Primary mark",       "url": "https://.../logo.svg",

"name": "Primary mark",       "url": "https://.../logo.svg",       "variant": "color",

"url": "https://.../logo.svg",