fix(voice): forward TTSModelSettings.speed to the OpenAI speech API - #4220
Merged
Conversation
seratch
approved these changes
Aug 5, 2026
seratch
enabled auto-merge (squash)
August 5, 2026 22:52
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TTSModelSettings.speedis a documented public setting ("Between 0.25 and 4.0") and it is even recorded on the speech span's model config, butOpenAITTSModel.runnever passes it toaudio.speech.with_streaming_response.create, so setting it has no effect on the generated audio. The OpenAI speech API takesspeedas a first-class parameter, so this forwards the configured value and falls back toomitwhen it is unset, leaving the current default behavior unchanged.Fail-before evidence: with the fix reverted via
git checkout upstream/main -- src/agents/voice/models/openai_tts.py, the newtest_openai_tts_forwards_speedfails withTypeError: fake_create() missing 1 required keyword-only argument: 'speed', and it passes with the fix restored.make format,make lint,make typecheckand the voice test suite are green.