Not in the top 1,000 by GitHub stars
ThePlasmak/faster-whisper
An OpenClaw skill that uses faster-whisper (a faster implementation of the Whisper transcription model) to transcribe audio, with additional features such as speaker diarization
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
1c8d6a682c56 → 1c8d6a682c56
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 1c8d6a682c56
No earlier version was observed for comparison.
10GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
faster-whisper
When your agent uses it
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
What it loads into context
Frontmatter
271 tokensAlways available to the agent
SKILL.md
15,834 tokensWhen the skill is activated
Reference documents
9,363 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Quick Reference
- Model Selection
- Custom & Fine-tuned Models
- Setup
- Usage
- Options
- Output Formats
- Speaker Diarization
- Precise Word Timestamps
- URL & YouTube Input
- Batch Processing
- Workflows
- Server Mode (OpenAI-Compatible API)
- Common Mistakes
- Performance Notes
- Why faster-whisper?
- Troubleshooting
- References
Scripts executed separately
scripts/transcribescripts/transcribe.cmdscripts/transcribe.ps1scripts/transcribe.pysetup.ps1setup.sh
Files
.clawdhubignoreasset75 bytes.gitignoreasset191 bytesCHANGELOG.mddoc10,556 bytesLICENSEasset1,067 bytesREADME.mddoc24,638 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesSKILL.mdcore67,024 bytesrequirements.txtdoc117 bytesscripts/transcriberuns881 bytesscripts/transcribe.cmdruns921 bytesscripts/transcribe.ps1runs2,437 bytesscripts/transcribe.pyruns114,264 bytessetup.ps1runs11,054 bytessetup.shruns12,721 bytesskill.jsonasset599 bytes
Read SKILL.md
# Faster Whisper
Local speech-to-text using faster-whisper — a CTranslate2 reimplementation of OpenAI's Whisper that runs **4-6x faster** with identical accuracy. With GPU acceleration, expect **~20x realtime** transcription (a 10-minute audio file in ~30 seconds).
## When to Use
Use this skill when you need to:
- **Transcribe audio/video files** — meetings, interviews, podcasts, lectures, YouTube videos
- **Generate subtitles** — SRT, VTT, ASS, LRC, or TTML broadcast-standard subtitles
- **Identify speakers** — diarization labels who said what (`--diarize`)
- **Transcribe from URLs** — YouTube links and direct audio URLs (auto-downloads via yt-dlp)
- **Transcribe podcast feeds** — `--rss <feed-url>` fetches and transcribes episodes
- **Batch process files** — glob patterns, directories, skip-existing support; ETA shown automaticallySkills included
- faster-whisper
Repository facts
- License
- MIT
- Created
- Jan 28, 2026
- Last pushed
- Feb 22, 2026
- Forks
- 4
- Open issues
- 1
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 21 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: SKILL.md:1
- 8 dangerous shell commandsin 2 files: README.md:422 setup.sh:196
- 124 network referencesin 5 files: SKILL.md:4 README.md:65 scripts/transcribe.py:367 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- 6 executable scriptsin 6 files: scripts/transcribe:1 scripts/transcribe.cmd:1 scripts/transcribe.ps1:1 and 3 more
- 4 references to secretsin 2 files: scripts/transcribe.py:1123 SKILL.md:966
- No requests to vote in Hot
Show all 143 signals by file
README.md
- Network accessline 65
1. Go to https://clawdhub.com/ThePlasmak/faster-whisper 2. Download the zip - Network accessline 71
1. Go to [Releases](https://github.com/ThePlasmak/faster-whisper/releases) 2. Download the latest `faster-whisper-X.X.X.zip` - Network accessline 83
**If you're lazy:** You can also ask your agent to install it by pasting this repo's link (https://github.com/ThePlasmak/faster-whisper) directly in the chat. - Network accessline 175
# YouTube / URL input (auto-downloads) ./scripts/transcribe https://youtube.com/watch?v=... --language en - Network accessline 176
./scripts/transcribe https://youtube.com/watch?v=... --language en - Network accessline 187
# Transcribe a podcast RSS feed (latest 5 episodes) ./scripts/transcribe --rss https://feeds.example.com/podcast.xml -o ./episodes/ - Network accessline 188
./scripts/transcribe --rss https://feeds.example.com/podcast.xml -o ./episodes/ - Dangerous shell operationline 422
sudo apt install nvidia-cuda-toolkit - Network accessline 451
If this fails, install/update your [NVIDIA drivers](https://www.nvidia.com/download/index.aspx) - Network accessline 453
2. **WSL2 users:** Install CUDA drivers on **Windows**, not inside WSL2 - Follow: [NVIDIA CUDA on WSL2 Guide](https://docs.nvidia.com/cuda/wsl-user-guide/) - Network accessline 454
- Follow: [NVIDIA CUDA on WSL2 Guide](https://docs.nvidia.com/cuda/wsl-user-guide/) - Network accessline 458
# Linux/macOS/WSL2 .venv/bin/pip install torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 459
.venv/bin/pip install torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 461
# Windows .venv\Scripts\pip install torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 462
.venv\Scripts\pip install torch --index-url https://download.pytorch.org/whl/cu121 - Dangerous shell operationline 527
sudo apt install ffmpeg - Dangerous shell operationline 530
sudo dnf install ffmpeg - Dangerous shell operationline 533
sudo pacman -S ffmpeg - Dangerous shell operationline 633
sudo apt install python3.12 python3.12-venv - Network accessline 642
2. **Check the logs:** Run without `--quiet` to see detailed error messages 3. **Ask your agent:** Paste the error — it can usually diagnose faster-whisper or installation issues 4. **Open an issue:** [GitHub Issues](https://github.com/TheP - Network accessline 643
3. **Ask your agent:** Paste the error — it can usually diagnose faster-whisper or installation issues 4. **Open an issue:** [GitHub Issues](https://github.com/ThePlasmak/faster-whisper/issues) 5. **Include:** - Network accessline 644
4. **Open an issue:** [GitHub Issues](https://github.com/ThePlasmak/faster-whisper/issues) - Network accessline 653
- **[parakeet](https://github.com/ThePlasmak/parakeet)** - Network accessline 659
- [faster-whisper GitHub](https://github.com/SYSTRAN/faster-whisper) - Network accessline 660
- [Distil-Whisper Paper](https://arxiv.org/abs/2311.00430) - Network accessline 661
- [OpenAI Whisper Models](https://github.com/openai/whisper#available-models-and-languages) - Network accessline 662
- [HuggingFace Models](https://huggingface.co/collections/Systran/faster-whisper) - [pyannote.audio](https://github.com/pyannote/pyannote-audio) (diarization) - [yt-dlp](https://github.com/yt-dlp/yt-dlp) (URL/YouTube download) - Network accessline 663
- [pyannote.audio](https://github.com/pyannote/pyannote-audio) (diarization) - Network accessline 664
- [yt-dlp](https://github.com/yt-dlp/yt-dlp) (URL/YouTube download)
SKILL.md
- Broad permissionsline 1
Unsupported or unresolved allowed-tools declaration - Network accessline 4
version: 1.5.1 author: ThePlasmak homepage: https://github.com/ThePlasmak/faster-whisper - Network accessline 5
author: ThePlasmak homepage: https://github.com/ThePlasmak/faster-whisper tags: - Network accessline 6
homepage: https://github.com/ThePlasmak/faster-whisper - Network accessline 196
| **Denoise + normalize** | `./scripts/transcribe audio.mp3 --denoise --normalize` | Clean up noisy audio first | | **Reduce hallucination** | `./scripts/transcribe audio - Network accessline 197
| **Reduce hallucination** | `./scripts/transcribe audio.mp3 --hallucination-silence-threshold 1.0` | Skip hallucinated silence | | **YouTube/URL** | `./scripts/transcribe https - Network accessline 198
| **YouTube/URL** | `./scripts/transcribe https://youtube.com/watch?v=...` | Auto-downloads via yt-dlp | - Network accessline 235
| **Name speakers** | `./scripts/transcribe audio.mp3 --diarize --speaker-names "Alice,Bob"` | Replaces SPEAKER_1/2 | | **Filter hallucinations** | `./scripts/transcribe audio - Network accessline 236
| **Filter hallucinations** | `./scripts/transcribe audio.mp3 --filter-hallucinations` | Removes artifacts | | **Keep temp files** | `./scripts/transcribe https - Network accessline 237
| **Keep temp files** | `./scripts/transcribe https://... --keep-temp` | For URL re-processing | - Network accessline 239
| **RTX 3070 recommended** | `./scripts/transcribe audio.mp3 --compute-type int8_float16` | Saves ~1GB VRAM, minimal quality loss | | **CPU thread count** | `./scripts/transcribe audio - Network accessline 240
| **CPU thread count** | `./scripts/transcribe audio.mp3 --threads 8` | Force CPU thread count (default: auto) | | **Podcast RSS (latest 5)** | `./scripts/transcribe --rss - Network accessline 241
| **Podcast RSS (latest 5)** | `./scripts/transcribe --rss https://feeds.example.com/podcast.xml` | Downloads & transcribes newest 5 episodes | - Network accessline 242
| **Podcast RSS (all episodes)** | `./scripts/transcribe --rss https://... --rss-latest 0 -o ./episodes/` | All episodes, one file each | - Network accessline 243
| **Podcast + SRT subtitles** | `./scripts/transcribe --rss https://... --format srt -o ./subs/` | Subtitle all episodes | - Network accessline 407
# For CUDA 12.x uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 408
uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 410
# For CUDA 11.x uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu118 - Network accessline 411
uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu118 - Network accessline 414
- **WSL2 users**: Ensure you have the [NVIDIA CUDA drivers for WSL](https://docs.nvidia.com/cuda/wsl-user-guide/) installed on Windows - Network accessline 428
# Transcribe from YouTube URL ./scripts/transcribe https://youtube.com/watch?v=dQw4w9WgXcQ --language en - Network accessline 429
./scripts/transcribe https://youtube.com/watch?v=dQw4w9WgXcQ --language en - Network accessline 756
Identifies who spoke when using [pyannote.audio](https://github.com/pyannote/pyannote-audio). - Network accessline 766
- HuggingFace token at `~/.cache/huggingface/token` (`huggingface-cli login`) - Accepted model agreements: - https://hf.co/pyannote/speaker-diarization-3.1 - Network accessline 767
- Accepted model agreements: - https://hf.co/pyannote/speaker-diarization-3.1 - https://hf.co/pyannote/segmentation-3.0 - Network accessline 768
- https://hf.co/pyannote/speaker-diarization-3.1 - Network accessline 769
- https://hf.co/pyannote/segmentation-3.0 - Network accessline 808
# YouTube video ./scripts/transcribe https://youtube.com/watch?v=dQw4w9WgXcQ - Network accessline 809
./scripts/transcribe https://youtube.com/watch?v=dQw4w9WgXcQ - Network accessline 811
# Direct audio URL ./scripts/transcribe https://example.com/podcast.mp3 - Network accessline 812
./scripts/transcribe https://example.com/podcast.mp3 - Network accessline 814
# With options ./scripts/transcribe https://youtube.com/watch?v=... --language en --format srt -o subs.srt - Network accessline 815
./scripts/transcribe https://youtube.com/watch?v=... --language en --format srt -o subs.srt - Network accessline 861
# Transcribe latest 5 episodes → one .txt per episode ./scripts/transcribe --rss https://feeds.megaphone.fm/mypodcast -o ./transcripts/ - Network accessline 862
./scripts/transcribe --rss https://feeds.megaphone.fm/mypodcast -o ./transcripts/ - Network accessline 864
# All episodes, as SRT subtitles ./scripts/transcribe --rss https://... --rss-latest 0 --format srt -o ./subtitles/ - Network accessline 865
./scripts/transcribe --rss https://... --rss-latest 0 --format srt -o ./subtitles/ - Network accessline 867
# Skip already-done episodes (safe to re-run) ./scripts/transcribe --rss https://... --skip-existing -o ./transcripts/ - Network accessline 868
./scripts/transcribe --rss https://... --skip-existing -o ./transcripts/ - Network accessline 870
# With diarization (who said what) + retry on flaky network ./scripts/transcribe --rss https://... --diarize --retries 2 -o ./transcripts/ - Network accessline 871
./scripts/transcribe --rss https://... --diarize --retries 2 -o ./transcripts/ - Network accessline 909
# One-liner: transcribe a playlist video + output SRT ./scripts/transcribe "https://youtube.com/watch?v=abc123" --format srt -o subs.srt - Network accessline 910
./scripts/transcribe "https://youtube.com/watch?v=abc123" --format srt -o subs.srt - Network accessline 915
# Download audio first, then transcribe (for re-use without re-downloading) ./scripts/transcribe https://youtube.com/watch?v=abc123 --keep-temp - Network accessline 916
./scripts/transcribe https://youtube.com/watch?v=abc123 --keep-temp - Network accessline 945
[speaches](https://github.com/speaches-ai/speaches) runs faster-whisper as an OpenAI-compatible `/v1/audio/transcriptions` endpoint — drop-in replacement for OpenAI Whisper API with streaming, Docker support, and live transcription. - Network accessline 956
# Transcribe a file via the API (same format as OpenAI) curl http://localhost:8000/v1/audio/transcriptions \ - Network accessline 957
curl http://localhost:8000/v1/audio/transcriptions \ - Network accessline 965
[Credential-related source omitted] - Network accessline 966
[Credential-related source omitted] - Access to secretsline 966
[Credential-related source omitted] - Network accessline 1126
- [faster-whisper GitHub](https://github.com/SYSTRAN/faster-whisper) - Network accessline 1127
- [Distil-Whisper Paper](https://arxiv.org/abs/2311.00430) - Network accessline 1128
- [HuggingFace Models](https://huggingface.co/collections/Systran/faster-whisper) - [pyannote.audio](https://github.com/pyannote/pyannote-audio) (diarization) - [yt-dlp](https://github.com/yt-dlp/yt-dlp) (URL/YouTube download) - Network accessline 1129
- [pyannote.audio](https://github.com/pyannote/pyannote-audio) (diarization) - Network accessline 1130
- [yt-dlp](https://github.com/yt-dlp/yt-dlp) (URL/YouTube download)
scripts/transcribe
- Executable scriptline 1
#!/usr/bin/env bash
scripts/transcribe.cmd
- Executable scriptline 1
Executable file
scripts/transcribe.ps1
- Executable scriptline 1
Executable file
scripts/transcribe.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 367
'<?xml version="1.0" encoding="UTF-8"?>', f'<tt xml:lang="{lang_attr}"', ' xmlns="http://www.w3.org/ns/ttml"', - Network accessline 368
f'<tt xml:lang="{lang_attr}"', ' xmlns="http://www.w3.org/ns/ttml"', ' xmlns:tts="http://www.w3.org/ns/ttml#styling"', - Network accessline 369
' xmlns="http://www.w3.org/ns/ttml"', - Network accessline 370
' xmlns:tts="http://www.w3.org/ns/ttml#styling"', - Network accessline 371
' xmlns:ttm="http://www.w3.org/ns/ttml#metadata">', - Network accessline 858
try: req = urllib.request.Request( - Network accessline 859
req = urllib.request.Request( - Network accessline 860
rss_url, headers={"User-Agent": "faster-whisper-skill/1.0"} ) with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 861
) with urllib.request.urlopen(req, timeout=30) as resp: xml_data = resp.read() - Network accessline 862
with urllib.request.urlopen(req, timeout=30) as resp: - Access to secretsline 1123
[Credential-related source omitted] - Network accessline 1130
print( " Ensure you have a HuggingFace token at ~/.cache/huggingface/token\n" " and accepted: https://hf.co/pyannote/speaker-diarization-3.1", - Network accessline 1131
" Ensure you have a HuggingFace token at ~/.cache/huggingface/token\n" " and accepted: https://hf.co/pyannote/speaker-diarization-3.1", file=sys.stderr, - Network accessline 1132
" and accepted: https://hf.co/pyannote/speaker-diarization-3.1", - Network accessline 1946
" %(prog)s audio.mp3\n" " %(prog)s audio.mp3 --format srt -o subtitles.srt\n" " %(prog)s https://youtube.com/watch?v=... --language en\n" - Network accessline 1947
" %(prog)s audio.mp3 --format srt -o subtitles.srt\n" " %(prog)s https://youtube.com/watch?v=... --language en\n" " %(prog)s *.mp3 --skip-existing -o ./transcripts/\n" - Network accessline 1948
" %(prog)s https://youtube.com/watch?v=... --language en\n" - Access to secretsline 2426
[Credential-related source omitted] - Access to secretsline 2427
[Credential-related source omitted] - Network accessline 2531
if device == "cpu" and not args.quiet: print("⚠<U+FE0F> CUDA not available — using CPU (this will be slow!)", file=sys.stderr) print(" To enable GPU: pip install torch --index-url https://download.pytorch.org/whl/cu121", - Network accessline 2533
print(" To enable GPU: pip install torch --index-url https://download.pytorch.org/whl/cu121", file=sys.stderr)
setup.ps1
- Executable scriptline 1
Executable file - Network accessline 151
} else { Write-Host "" Write-Host "Please install Python 3.10+ manually from https://python.org" -ForegroundColor Yellow - Network accessline 152
Write-Host "" Write-Host "Please install Python 3.10+ manually from https://python.org" -ForegroundColor Yellow Write-Host "Make sure to check 'Add Python to PATH' during installation." -ForegroundColor Yello - Network accessline 153
Write-Host "Please install Python 3.10+ manually from https://python.org" -ForegroundColor Yellow - Network accessline 156
} } else { Write-Host "Please install Python 3.10+ from https://python.org" -ForegroundColor Yellow - Network accessline 157
} else { Write-Host "Please install Python 3.10+ from https://python.org" -ForegroundColor Yellow Write-Host "Make sure to check 'Add Python to PATH' during installation." -ForegroundColor Yellow - Network accessline 158
Write-Host "Please install Python 3.10+ from https://python.org" -ForegroundColor Yellow - Network accessline 175
Write-Host "Please install ffmpeg manually:" -ForegroundColor Yellow Write-Host " Option 1: winget install Gyan.FFmpeg" -ForegroundColor White Write-Host " Option 2: Download from https://ffmpeg.org" -Foreg - Network accessline 176
Write-Host " Option 1: winget install Gyan.FFmpeg" -ForegroundColor White Write-Host " Option 2: Download from https://ffmpeg.org" -ForegroundColor White Write-Host "" - Network accessline 177
Write-Host " Option 2: Download from https://ffmpeg.org" -ForegroundColor White - Network accessline 183
Write-Host "Please install ffmpeg:" -ForegroundColor Yellow Write-Host " Option 1: winget install Gyan.FFmpeg" -ForegroundColor White Write-Host " Option 2: Download from https://ffmpeg.org" -ForegroundColor White - Network accessline 184
Write-Host " Option 1: winget install Gyan.FFmpeg" -ForegroundColor White Write-Host " Option 2: Download from https://ffmpeg.org" -ForegroundColor White Write-Host "" - Network accessline 185
Write-Host " Option 2: Download from https://ffmpeg.org" -ForegroundColor White - Network accessline 278
if (Test-Command "uv") { & uv pip install --python $venvPython torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 279
& uv pip install --python $venvPython torch --index-url https://download.pytorch.org/whl/cu121 - Network accessline 280
} else { & $venvPython -m pip install torch --index-url https://download.pytorch.org/whl/cu121 } - Network accessline 281
& $venvPython -m pip install torch --index-url https://download.pytorch.org/whl/cu121
setup.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 147
echo " --diarize Also install pyannote.audio for speaker diarization" echo " Requires HuggingFace token at ~/.cache/huggingface/token" echo " and model agreement at https://hf.co/pyann - Network accessline 148
echo " Requires HuggingFace token at ~/.cache/huggingface/token" echo " and model agreement at https://hf.co/pyannote/speaker-diarization-3.1" echo " --update Upgrade faster-whisper i - Network accessline 149
echo " and model agreement at https://hf.co/pyannote/speaker-diarization-3.1" - Dangerous shell operationline 196
echo " Ubuntu/Debian: sudo apt install ffmpeg" - Dangerous shell operationline 197
echo " Fedora: sudo dnf install ffmpeg" - Dangerous shell operationline 198
echo " Arch: sudo pacman -S ffmpeg" - Network accessline 283
echo "" if command -v uv &> /dev/null; then uv pip install --python "$VENV_DIR/bin/python" torch torchaudio --index-url https://download.pytorch.org/whl/cu121 - Network accessline 284
if command -v uv &> /dev/null; then uv pip install --python "$VENV_DIR/bin/python" torch torchaudio --index-url https://download.pytorch.org/whl/cu121 else - Network accessline 285
uv pip install --python "$VENV_DIR/bin/python" torch torchaudio --index-url https://download.pytorch.org/whl/cu121 - Network accessline 286
else "$VENV_DIR/bin/pip" install torch torchaudio --index-url https://download.pytorch.org/whl/cu121 fi - Network accessline 287
"$VENV_DIR/bin/pip" install torch torchaudio --index-url https://download.pytorch.org/whl/cu121 - Network accessline 315
echo " Diarization requires:" echo " 1. A HuggingFace account and token (huggingface-cli login)" echo " 2. Accept model agreement: https://hf.co/pyannote/speaker-diarization-3.1" - Network accessline 316
echo " 1. A HuggingFace account and token (huggingface-cli login)" echo " 2. Accept model agreement: https://hf.co/pyannote/speaker-diarization-3.1" echo " 3. Accept model agreement: https://hf.co/pyannote/segmentation - Network accessline 317
echo " 2. Accept model agreement: https://hf.co/pyannote/speaker-diarization-3.1" - Network accessline 318
echo " 3. Accept model agreement: https://hf.co/pyannote/segmentation-3.0"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Declared and executed: 3 facts
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/transcribe.py:369High confidence
- Contacts python.org, which SKILL.md, the README and the plugin manifest do not mentionsetup.ps1:153High confidence
- Contacts ffmpeg.org, which SKILL.md, the README and the plugin manifest do not mentionsetup.ps1:177High confidence
Signal confidence: 143 facts
- Network access in prose of documentationREADME.md:65Low confidence
- Network access in prose of documentationREADME.md:71Low confidence
- Network access in prose of documentationREADME.md:83Low confidence
- Network access in code of documentationREADME.md:175Low confidence
- Network access in code of documentationREADME.md:176Low confidence
- Network access in code of documentationREADME.md:187Low confidence
- Network access in code of documentationREADME.md:188Low confidence
- Dangerous shell operation in code of documentationREADME.md:422Low confidence
- Network access in prose of documentationREADME.md:451Low confidence
- Network access in prose of documentationREADME.md:453Low confidence
- Network access in prose of documentationREADME.md:454Low confidence
- Network access in code of documentationREADME.md:458Low confidence
- Network access in code of documentationREADME.md:459Low confidence
- Network access in code of documentationREADME.md:461Low confidence
- Network access in code of documentationREADME.md:462Low confidence
- Dangerous shell operation in code of documentationREADME.md:527Low confidence
- Dangerous shell operation in code of documentationREADME.md:530Low confidence
- Dangerous shell operation in code of documentationREADME.md:533Low confidence
- Dangerous shell operation in code of documentationREADME.md:633Low confidence
- Network access in prose of documentationREADME.md:642Low confidence
- Network access in prose of documentationREADME.md:643Low confidence
- Network access in prose of documentationREADME.md:644Low confidence
- Network access in prose of documentationREADME.md:653Low confidence
- Network access in prose of documentationREADME.md:659Low confidence
- Network access in prose of documentationREADME.md:660Low confidence
- Network access in prose of documentationREADME.md:661Low confidence
- Network access in prose of documentationREADME.md:662Low confidence
- Network access in prose of documentationREADME.md:663Low confidence
- Network access in prose of documentationREADME.md:664Low confidence
- Broad permissions in the frontmatter of the SKILL.mdSKILL.md:1High confidence
- Network access in the frontmatter of the SKILL.mdSKILL.md:4Low confidence
- Network access in the frontmatter of the SKILL.mdSKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdSKILL.md:6Low confidence
- Network access in prose of the SKILL.mdSKILL.md:196Low confidence
- Network access in prose of the SKILL.mdSKILL.md:197Low confidence
- Network access in prose of the SKILL.mdSKILL.md:198Low confidence
- Network access in prose of the SKILL.mdSKILL.md:235Low confidence
- Network access in prose of the SKILL.mdSKILL.md:236Low confidence
- Network access in prose of the SKILL.mdSKILL.md:237Low confidence
- Network access in prose of the SKILL.mdSKILL.md:239Low confidence
- Network access in prose of the SKILL.mdSKILL.md:240Low confidence
- Network access in prose of the SKILL.mdSKILL.md:241Low confidence
- Network access in prose of the SKILL.mdSKILL.md:242Low confidence
- Network access in prose of the SKILL.mdSKILL.md:243Low confidence
- Network access in code of the SKILL.mdSKILL.md:407High confidence
- Network access in code of the SKILL.mdSKILL.md:408High confidence
- Network access in code of the SKILL.mdSKILL.md:410High confidence
- Network access in code of the SKILL.mdSKILL.md:411High confidence
- Network access in prose of the SKILL.mdSKILL.md:414Low confidence
- Network access in code of the SKILL.mdSKILL.md:428High confidence
and 93 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
