I’m trying to use Whisper API and it worked when I upload my local audio file. Now when I try to develop it as an endpoint in FastAPI, the API would not accept the file, throwing an Invalid Request Error.
@app.post("/audio")
async def summarise_audio(file:UploadFile):
audio =await file.read()
with open("testy.wav",'wb') as f:
f.write(audio)
x = open("testy.wav",'rb')
transcript = openai.Audio.transcribe("whisper-1",x)
# transcript = openai.Audio.transcribe("whisper-1",file.file)
return transcript
It worked when I read the received file and save it into the disk and then opening it from disk.
But when I use the file directly from the endpoint, it is throwing InvalidRequestError
openai.error.InvalidRequestError: Invalid file format. Supported formats: ['m4a', 'mp3', 'webm', 'mp4', 'mpga', 'wav', 'mpeg']