Update Speech-to-Speech docs with OpenAI Realtime API schema #565
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
- Add beta warning prominently at the top - Update to use new API endpoint (wss://speech-to-speech.assemblyai.com/v1/realtime) - Add WebSocket code examples for Python and JavaScript - Add OpenAI Python client example - Add LiveKit integration with full agent example - Add Pipecat integration with full pipeline example - Add tool calling documentation and examples - Add subagent routing documentation with multi-agent example - Add complete sample agents: - Debt collection agent with FDCPA compliance - Interview agent with scoring and notes - Lead qualification agent with BANT methodology - Add WebSocket events reference (client and server events) - Add roadmap and known issues sections - Remove unhelpful ASCII diagram - Reorganize content for better readability Co-Authored-By: Dan Ince <dince@assemblyai.com>
Contributor
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
Co-Authored-By: Dan Ince <dince@assemblyai.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Update Speech-to-Speech docs with OpenAI Realtime API schema
Summary
Rewrites the Speech-to-Speech documentation to reflect the new API that mirrors the OpenAI Realtime API schema. The new docs use the endpoint
wss://speech-to-speech.assemblyai.com/v1/realtimeand include comprehensive code examples for multiple integration patterns.Key changes:
Review & Testing Checklist for Human
wss://speech-to-speech.assemblyai.com/v1/realtimeis correct and the event types (session.update,response.audio.delta,conversation.item.input_audio_transcription.completed, etc.) match the actual APIsage,coral,verse,alloyare the correct voice options for this APIfrom livekit.plugins.openai.realtime import AudioTranscription) and configuration work correctlyfern docs devlocally: Preview the rendered documentation to ensure formatting looks correctRecommended test plan: Run one of the Python WebSocket examples against the actual API to verify the connection flow, event types, and audio handling work as documented.
Notes
[docs]: All checks passed)