Add OpenAI Realtime API speech-to-speech architecture #74
+1,385
−8
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Implemented a new direct speech-to-speech voice agent using OpenAI's Realtime API (gpt-4o-realtime-preview) with clean separation of concerns. Key features: - Direct speech-to-speech (no chained STT → GPT → TTS) - WebSocket-based architecture with Twilio MediaStreams - Native g711_ulaw (μ-law) audio format support - Intelligent interruption/barge-in handling - Automatic reconnection and error handling - Clean modular structure in /src directory Architecture: - src/openai/realtimeClient.js - OpenAI Realtime WebSocket client - src/core/callSession.js - Session orchestrator - src/twilio/twilioServer.js - Twilio MediaStream server - src/index.js - Main entry point Added: - New npm scripts: 'realtime' and 'realtime:dev' - Comprehensive README.realtime.md with setup guide - .env.realtime.example for configuration - ws package dependency for WebSocket client The old chained architecture (app.js) remains intact for backward compatibility. Run with: npm run realtime
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implemented a new direct speech-to-speech voice agent using OpenAI's Realtime API (gpt-4o-realtime-preview) with clean separation of concerns.
Key features:
Architecture:
Added:
The old chained architecture (app.js) remains intact for backward compatibility.
Run with: npm run realtime
Contributing to Twilio