Skip to content

ENG-86341: docs: note Kokoro voice mixing syntax on audio-speech voice field#244

Merged
rishabh-bhargava merged 2 commits intomainfrom
fix/kokoro-voice-mixing
Apr 25, 2026
Merged

ENG-86341: docs: note Kokoro voice mixing syntax on audio-speech voice field#244
rishabh-bhargava merged 2 commits intomainfrom
fix/kokoro-voice-mixing

Conversation

@rishabh-bhargava
Copy link
Copy Markdown
Contributor

Summary

  • hexgrad/Kokoro-82M supports combining voices via voiceA+voiceB (equal weights) or voiceA(2)+voiceB(1) (weighted). Other TTS models require a single voice name.
  • This updates the voice field description on the audio-speech request schema so API consumers see the syntax inline, alongside the existing voice guidance.
  • Companion to inference-pop #1803 (validator fix) and mintlify-docs #707 (user-facing docs).

Test plan

  • Generated API reference renders the new description correctly
  • SDK regeneration (if auto-triggered) picks up the updated schema without breaking types

🤖 Generated with Claude Code

hexgrad/Kokoro-82M supports combining voices via "voiceA+voiceB" (equal
weights) or "voiceA(2)+voiceB(1)" (weighted). Mention the syntax on the
voice field description so API consumers see it inline with the other
voice guidance.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Apr 20, 2026

✱ Stainless preview builds

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

go

docs(api): document voice mixing support for audio speech voice parameter

openapi

docs(api): update voice parameter description with voice mixing details

python

docs(api): document voice mixing for speech voice parameter

terraform

chore(internal): regenerate SDK with no functional changes

typescript

docs(api): document voice mixing support for speech voice parameter
togetherai-openapi studio · code

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

⚠️ togetherai-python studio · code

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

pip install https://pkg.stainless.com/s/togetherai-python/15aab9c8ad0d3470bdea1e654127bcbd02e71c5c/together-2.10.0-py3-none-any.whl
⚠️ 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@374f51bb529fd6271283a4b25a63b5e4f80dfe6c
⚠️ togetherai-typescript studio · conflict

Your SDK build had at least one warning diagnostic.

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: 2026-04-25 19:51:48 UTC

@rishabh-bhargava rishabh-bhargava changed the title docs: note Kokoro voice mixing syntax on audio-speech voice field ENG-86341: docs: note Kokoro voice mixing syntax on audio-speech voice field Apr 20, 2026
Resolved conflict in openapi.yaml: main collapsed the voice field
description onto a single line via yamlfmt (#248). Reapplied the
Kokoro voice mixing sentence to the same single-line block.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@rishabh-bhargava rishabh-bhargava merged commit 06addb0 into main Apr 25, 2026
6 checks passed
@rishabh-bhargava rishabh-bhargava deleted the fix/kokoro-voice-mixing branch April 25, 2026 19:49
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