Open
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
LArmstrongDev
commented
Mar 19, 2026
LArmstrongDev
commented
Mar 24, 2026
LArmstrongDev
commented
Mar 24, 2026
LArmstrongDev
commented
Mar 24, 2026
LArmstrongDev
commented
Mar 24, 2026
Contributor
Author
|
Todo - add clarity on supported languages. |
Clarifies that only pcm_s16le at 8000/16000 Hz is supported. Other formats may be silently accepted but will not produce correct output.
- Add real payloads and field descriptions for EndOfTurnPrediction, SmartTurnResult, SpeechStarted and SpeechEnded - Rename SmartTurnPrediction to SmartTurnResult throughout (mermaid diagram, messages table, section header) - Add audio format warning and example to audio_format section
The payload is already documented in the SpeakersResult server message section. Replace with links to the API reference entries for GetSpeakers and SpeakersResult.
…ocks - Fix ordering: SpeakerStarted after StartOfTurn, SpeechEnded/EndOfUtterance/ SpeakerEnded before AddSegment, EndOfTurn last - Add missing EndOfUtterance - Remove incorrect Speaker activity opt block — speaker events now in correct position in the main flow - Add profile annotations inline (adaptive/smart, smart only, external only) - Move ForceEndOfUtterance into mid-session controls opt block - Add SessionMetrics note below diagram
Move language info out of Trade-off text into a dedicated Languages field, consistent with Best for / Trade-off pattern. All profiles now explicitly state language support.
Contributor
Author
|
The additional changes all LGTM - and ticks off all the outstanding todos. Thanks for picking those up, @ArchieMcM234! |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
This MR includes improvements to the Preview docs for the Voice Agent API. These changes are necessary for bringing the docs up to standard, providing the complete information needed for testing, and API spec details.
Changes include:
SmartTurnResultto match current API behaviour)