BerriAI/litellm · error · ValueError

Invalid response format. Received response does not match th

Error message

Invalid response format. Received response does not match the expected format. Got: {raw_response_json}

What it means

ValueError from the Whisper transcription response transformer: the body parsed as JSON but contains none of the fields expected of a TranscriptionResponse (e.g. 'text'), so it cannot be mapped. Typically a provider returned an unexpected JSON schema (error object or vendor-specific shape) for a transcription request.

Source

Thrown at litellm/llms/openai/transcriptions/whisper_transformation.py:138

            headers=headers,
        )

    def transform_audio_transcription_response(
        self,
        raw_response: Response,
    ) -> TranscriptionResponse:
        try:
            raw_response_json: Final = raw_response.json()
        except json.JSONDecodeError:
            content_type: Final = raw_response.headers.get("content-type", "").lower()
            if "application/json" in content_type:
                raise
            return TranscriptionResponse(text=raw_response.text)

        if any(key in raw_response_json for key in TranscriptionResponse.model_fields):
            return TranscriptionResponse(**raw_response_json)
        else:
            raise ValueError(
                "Invalid response format. Received response does not match the expected format. Got: ",
                raw_response_json,
            )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check the received response shown in the message; ensure you are calling a transcription endpoint with a Whisper-compatible model and valid audio file.

When it happens

Trigger: Thrown at litellm/llms/openai/transcriptions/whisper_transformation.py:138 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/e280b5d2b797b5a7. Report an issue: GitHub.