Menu

Individual skill

crestapps-core-realtime-voice

Skill for realtime speech-to-speech voice in CrestApps.Core 2.0. Covers the realtime deployment capability and slot, Conversation chat mode with ConversationDeploymentName on profiles and chat interactions, ResolveConversationModeAsync, cascaded realtime deployments with CascadedRealtimeMetadata chaining speech-to-text, chat and text-to-speech legs, the CrestApps.Core.AI.WebRTC server-relay transport registered with AddWebRtcRealtimeTransport and its WebSocket fallback, RealtimeTransportOptions (idle timeout, max duration, semantic turn detection, knowledge grounding, STUN and TURN), coturn and Cloudflare TURN, custom IRealtimeIceServerProvider, IRealtimeOrchestrator and IRealtimeConversation, user transcription, the realtime hub methods and ReceiveRealtimeEvent contract, the CoreAIRealtime browser client, and upgrading from 1.x. Use it when adding voice to a chat surface, configuring TURN, building a cascade, or troubleshooting silent sessions, fallbacks, or missing transcripts.

plugins/crestapps-core/skills/crestapps-core-realtime-voice/SKILL.md

Read pinned source

Source commit d86d04f234b1b2bd8145368a2544490f9d557596

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
13
Repository last updated
Oct 21, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# CrestApps.Core Realtime Voice

A realtime session is a live, spoken conversation: audio in, audio out, with barge-in. It runs through the same orchestration as text chat, so the profile's or interaction's system message, persona, tools, data sources and turn persistence all apply. Audio travels over **WebRTC** (server relay) when available and falls back to **WebSocket** (PCM over SignalR) automatically.

## Guidelines

- Realtime is a model capability, not a chat mode. Declare the `realtime` feature on the deployment; it then fills the `realtime` slot. Never add `textGeneration` to a speech-to-speech-only model.
- A profile speaks when its chat mode is `Conversation` and a realtime deployment resolves. A chat interaction speaks when `ConversationDeploymentName` is set.
- Providers with a native realtime client in CrestApps.Core are OpenAI and Azure OpenAI (`gpt-realtime`). For anything else, build a cascaded realtime deployment.
- Register `AddWebRtcRealtimeTransport()` for production voice, and configure TURN so users behind strict NATs are not pushed to WebSocket after an 8-second wait.
- Add a speech-to-text deployment on the realtime deployment's provider (for example `gpt-4o-transcribe`), or the user's turns are not transcribed.
- Keep a voice profile's tool list short; every tool sits in the model's context on every turn.
- The chat hubs and UI are covered by `crestapps-core-chat-interactions`, hub options by `crestapps-core-signalr`, and provider configuration by `crestapps-core-openai` and `crestapps-core-azure-openai`.