Improve speech-to-text audio handling

Enhanced the audio processing in speech-to-text conversion by converting the input audio to MP3 format before transcription. The logging now reflects the word count of the recognized text, providing clearer insight into the output. This should improve compatibility with the transcription service and result in more accurate transcriptions.
This commit is contained in:
Kumi 2023-11-29 12:30:26 +01:00
parent eba650188b
commit 03768b5b27
Signed by: kumi
GPG key ID: ECBCC9082395383F

View file

@ -408,14 +408,18 @@ Only the event_types mentioned above are allowed, you must not respond in any ot
"""
self.logger.log(f"Generating text from speech...")
audio_file = BytesIO()
AudioSegment.from_file(BytesIO(audio)).export(audio_file, format="mp3")
audio_file.name = "audio.mp3"
response = await self.openai_api.audio.transcriptions.create(
model=self.stt_model,
file=BytesIO(audio),
file=audio_file,
)
text = response.text
self.logger.log(f"Generated text with {tokens_used} tokens.")
self.logger.log(f"Recognized text: {len(text.split())} words.")
return text