BerriAI/litellm · error · ValueError
Error transforming Deepgram response: {e} Response: {raw_res
Error message
Error transforming Deepgram response: {e}
Response: {raw_response.text} What it means
Error "Error transforming Deepgram response: {e} Response: {raw_response.text}" thrown in BerriAI/litellm.
Source
Thrown at litellm/llms/deepgram/audio_transcription/transformation.py:126
detected_language: Final = first_channel.get("detected_language")
response["language"] = detected_language if detected_language else "en"
response["duration"] = response_json["metadata"]["duration"]
# Transform words to match OpenAI format
if "words" in first_alternative:
response["words"] = [
{"word": word["word"], "start": word["start"], "end": word["end"]}
for word in first_alternative["words"]
]
# Store full response in hidden params
response._hidden_params = response_json
return response
except Exception as e:
raise ValueError(f"Error transforming Deepgram response: {e}\nResponse: {raw_response.text}")
def _reconstruct_diarized_transcript(self, words: list) -> str:
"""
Reconstructs a diarized transcript from words with speaker information.
Args:
words: List of word objects with speaker, word, and optionally punctuated_word
Returns:
Formatted transcript with speaker labels
"""
if not words:
return ""
segments: Final = []
current_speaker = None
current_words: list[str] = []
View on GitHub (pinned to 6c2dcb801b)
Solutions
- Inspect the Deepgram response body; check the audio format and request parameters.
When it happens
Trigger: Thrown at litellm/llms/deepgram/audio_transcription/transformation.py:126 when the library encounters an invalid state.
Common situations: See trigger scenarios.
AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15).
Data as JSON: /api/errors/7e7d5d86a78c202b.
Report an issue: GitHub.