Skip to content

MLE-5017: docs: add VAD/turn_detection params to realtime transcription endpoint#243

Merged
rishabh-bhargava merged 1 commit intomainfrom
feature/mle-5017-vad-openapi-docs
Apr 17, 2026
Merged

MLE-5017: docs: add VAD/turn_detection params to realtime transcription endpoint#243
rishabh-bhargava merged 1 commit intomainfrom
feature/mle-5017-vad-openapi-docs

Conversation

@rishabh-bhargava
Copy link
Copy Markdown
Contributor

Summary

Documents the Voice Activity Detection (VAD) configuration for the /realtime WebSocket transcription endpoint. This was previously completely undocumented despite being actively used by customers.

What's added

New client event:

  • transcription_session.updated — configure VAD parameters or disable VAD entirely

VAD parameters table (5 client-settable params with production defaults):

  • threshold (default 0.3)
  • min_silence_duration_ms (default 500)
  • min_speech_duration_ms (default 250)
  • max_speech_duration_s (default 5.0)
  • speech_pad_ms (default 250)

VAD disable/enable:

  • turn_detection: null in session message to disable
  • turn_detection=none query parameter to disable at connection time
  • Documents behavior difference: VAD on = auto completed events; VAD off = manual commit required

New server event:

  • transcription_session.updated — confirms VAD config was applied

Query parameter support:

  • Documents that all VAD params can be set as URL query parameters at connection time

Defaults verified against

Production defaults from inference-pop/src/v1/realtime.ts (lines 403-414), NOT the vad-service Python fallbacks which differ.

🤖 Generated with Claude Code

Document the Voice Activity Detection configuration for the /realtime
WebSocket endpoint:

- Add transcription_session.updated client event with turn_detection schema
- Document all 5 client-settable VAD parameters with production defaults
- Document how to disable VAD (turn_detection: null or query param none)
- Document query parameter configuration at connection time
- Document VAD on/off behavior (auto completed events vs manual commit)
- Add transcription_session.updated server confirmation event

MLE-5017

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@github-actions
Copy link
Copy Markdown

github-actions bot commented Apr 17, 2026

✱ Stainless preview builds

This PR will update the togetherai SDKs with the following commit messages.

go

chore(internal): regenerate SDK with no functional changes

openapi

docs: add VAD parameters and session update events to transcription WebSocket

python

chore(internal): regenerate SDK with no functional changes

terraform

chore(internal): regenerate SDK with no functional changes

typescript

chore(internal): regenerate SDK with no functional changes
togetherai-openapi studio · code

Your SDK build had at least one "note" diagnostic.
generate ✅

⚠️ togetherai-typescript studio · code

Your SDK build had a failure in the test CI job, which is a regression from the base state.
generate ⚠️build ⏭️lint ⏭️test ❗

⚠️ togetherai-python studio · code

Your SDK build had at least one "warning" diagnostic.
generate ⚠️build ⏭️lint ⏭️test ⏭️

⚠️ togetherai-go studio · code

Your SDK build had a failure in the test CI job, which is a regression from the base state.
generate ✅build ⏭️lint ✅test ❗

go get github.com/stainless-sdks/togetherai-go@6d1a3a5a40979fd15597646924da29d6235fbec6
togetherai-terraform studio · code

Your SDK build had at least one "note" diagnostic.
generate ✅lint ✅test ✅


This comment is auto-generated by GitHub Actions and is automatically kept up to date as you push.
If you push custom code to the preview branch, re-run this workflow to update the comment.
Last updated: 2026-04-17 23:23:05 UTC

@rishabh-bhargava rishabh-bhargava merged commit fb93ccc into main Apr 17, 2026
5 checks passed
@rishabh-bhargava rishabh-bhargava deleted the feature/mle-5017-vad-openapi-docs branch April 17, 2026 23:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants