fix: document per-model response_encoding and sample_rate behavior

[rishabh-bhargava]

Summary

Clarify in the OpenAPI spec that response_encoding and sample_rate behavior varies by model.

Changes

response_encoding: Added note that only Cartesia models respect this parameter. Orpheus, Kokoro, and Minimax always return pcm_s16le regardless of this setting.

sample_rate: Added note that only Cartesia and Minimax models respect this parameter. Orpheus and Kokoro always output at 24000 Hz regardless.

Defaults unchanged (pcm_f32le and 44100) since that's what inference-pop sends — the descriptions now clarify per-model behavior so users know what to expect.

Context

Tracked in Linear: MLE-5155

🤖 Generated with Claude Code

[github-actions]

✱ Stainless preview builds

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

go

docs(api): update sample_rate and response_encoding parameter docs in audiospeech

openapi

docs(api): clarify response_encoding and sample_rate parameter descriptions

python

docs(api): update response_encoding and sample_rate descriptions in audio speech

terraform

chore(internal): regenerate SDK with no functional changes

typescript

docs(api): update response_encoding and sample_rate descriptions in speech

✅ togetherai-openapi studio · code

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

⚠️ 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@e1b61d9e4718f75de57600ed247287cde4830d9d

⚠️ 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/bff30bd5034ffd182fdd9992adcd8aa2dff00506/together-2.10.0-py3-none-any.whl

⚠️ 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: 2026-04-27 03:50:05 UTC