Skip to content

MLE-5322: docs(audio): clarify prompt is Whisper-only#270

Merged
rishabh-bhargava merged 1 commit intomainfrom
feat/audio-prompt-whisper-only
May 7, 2026
Merged

MLE-5322: docs(audio): clarify prompt is Whisper-only#270
rishabh-bhargava merged 1 commit intomainfrom
feat/audio-prompt-whisper-only

Conversation

@rishabh-bhargava
Copy link
Copy Markdown
Contributor

Summary

Updates the prompt field description on both AudioTranscriptionRequest and AudioTranslationRequest to call out that it is supported only on Whisper-family models. Other STT models (Parakeet) accept the field for API compatibility but ignore it.

Fixes MLE-5322.

Why

prompt is a Whisper-style decoder-priming hint. Parakeet is a CTC/Transducer model with no slot for it — tvllm/inference_worker/parakeet_engine.py reads params.request_data but never accesses prompt. Behavioral test confirms: same audio + temperature=0, with vs without prompt, returns byte-identical text on Parakeet and dramatically different text on Whisper.

Test plan

  • Mintlify replication picks up the description change automatically (no action needed in mintlify-docs/openapi.yaml).
  • Companion guide-page change in togethercomputer/mintlify-docs (separate PR).

🤖 Generated with Claude Code

Both /audio/transcriptions and /audio/translations expose `prompt`, but it
only takes effect on Whisper-family models. Parakeet silently ignores it.
Update the field description so users don't copy-paste Whisper code with
prompt and expect biasing on Parakeet.
@github-actions
Copy link
Copy Markdown

github-actions Bot commented May 7, 2026

✱ Stainless preview builds

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

go

docs(api): clarify prompt parameter docs in transcription/translation

openapi

docs(api): clarify prompt parameter support in STT models

python

docs(api): clarify prompt parameter support in audio transcriptions/translations

terraform

chore(internal): regenerate SDK with no functional changes

typescript

docs(api): update prompt parameter description in audio transcriptions/translations
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@637afa209837f412dab07a0ecc8322ff8a10f6d3
⚠️ 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/9889ead58a66864a37d01ef0bbe92b4bc8786ff5/together-2.12.0-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: 2026-05-07 22:17:49 UTC

Copy link
Copy Markdown

@sbeurnier sbeurnier left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

theres a limit to the tokens for the promot, anything past that and we get silent 200 empty transcript. on our end we should fix to truncate user-passed prompt to fit within the limit but we should mention in docs the existence of such a limit (we can also rebuild engine to increase the limit beyond what it currently is)

@rishabh-bhargava
Copy link
Copy Markdown
Contributor Author

theres a limit to the tokens for the promot, anything past that and we get silent 200 empty transcript. on our end we should fix to truncate user-passed prompt to fit within the limit but we should mention in docs the existence of such a limit (we can also rebuild engine to increase the limit beyond what it currently is)

prompt is not working correctly anyway. I think we need to do that separately, here I am simply trying to clarify that it does not apply to Parakeet

@yadavsahil197
Copy link
Copy Markdown
Contributor

can we remove the prompt field entirely? It doesnt work well with whisper, we dont receomment people using it. I don't feel the point of having this field

@rishabh-bhargava rishabh-bhargava merged commit e42e72e into main May 7, 2026
6 checks passed
@rishabh-bhargava
Copy link
Copy Markdown
Contributor Author

rishabh-bhargava commented May 7, 2026 via email

@rishabh-bhargava rishabh-bhargava deleted the feat/audio-prompt-whisper-only branch May 7, 2026 22:15
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.

3 participants