When adding timestamp_granularities to the whisper API, I get:
TypeError: Transcriptions.create() got an unexpected keyword argument 'timestamp_granularities'
The code I’m running to do this is straight from the documentation here:
https://platform.openai.com/docs/api-reference/audio/createTranscription?lang=python
audio_file = open(“sample.mp3”, “rb”)
transcript = openai_client.audio.transcriptions.create(
file=audio_file,
model=“whisper-1”,
response_format=“verbose_json”,
timestamp_granularities=[“word”]
)
When removing timestamp_granularities=["word"], the code completes fine and as expected:
audio_file = open(“dream-machine-test.mp3”, “rb”)
transcript = openai_client.audio.transcriptions.create(
file=audio_file,
model=“whisper-1”,
response_format=“verbose_json”,
)
print(transcript)
Has timestamp_granularities been depreciated? I have confirmed I’m using openai 1.51.2 , is there something I’m missing here?
Very much appreciate the help.