From b4832e0c5d5e9e8f42178d05682d0fcea5eb8fd7 Mon Sep 17 00:00:00 2001 From: Rishabh Bhargava Date: Thu, 7 May 2026 14:44:44 -0700 Subject: [PATCH] MLE-5322: docs(audio): clarify prompt is Whisper-only 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. --- openapi.yaml | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/openapi.yaml b/openapi.yaml index 2cf5f37..3aba7df 100644 --- a/openapi.yaml +++ b/openapi.yaml @@ -10165,7 +10165,11 @@ components: example: en prompt: type: string - description: Optional text to bias decoding. + description: >- + Optional text to bias decoding. Supported only on Whisper-family + models (e.g. `openai/whisper-large-v3`). Other STT models + (e.g. `nvidia/parakeet-tdt-0.6b-v3`) accept the field for API + compatibility but ignore it. response_format: type: string description: The format of the response @@ -10400,7 +10404,11 @@ components: example: en prompt: type: string - description: Optional text to bias decoding. + description: >- + Optional text to bias decoding. Supported only on Whisper-family + models (e.g. `openai/whisper-large-v3`). Other STT models + (e.g. `nvidia/parakeet-tdt-0.6b-v3`) accept the field for API + compatibility but ignore it. response_format: type: string description: The format of the response