feat(voice): expose streamed transcription options - #4645
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: d1a414ff56
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
d1a414f to
b11b3bf
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b11b3bfbd3
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
b11b3bf to
0cdb420
Compare
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0cdb4204db
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Co-authored-by: abhay-codes07 <abhaysingh0293@gmail.com>
0cdb420 to
c75a6fa
Compare
This pull request supersedes #4616 and adds GA Realtime transcription options to streamed VoicePipeline speech-to-text sessions.
It appends optional
languages,keywords, anddelayfields toSTTModelSettings, forwards configured values in the existing streamed session payload, and records them in transcription trace metadata. Explicitlanguagestakes precedence over the legacy singularlanguagesetting, while unset options preserve the existing payload exactly.The change preserves the released constructor field order and existing static transcription, turn-detection, audio streaming, and session-completion behavior. Manual turn boundaries and
gpt-realtime-whisperlifecycle support remain out of scope.