Manual End of Speech
Closed this issue · 3 comments
Proposed changes
I believe it would be beneficial to incorporate a feature in the SDK for detecting a token at the end of speech to ensure accurate end-of-speech detection. This would provide a more reliable way to indicate the end of speech, especially in cases where automatic detection may be imperfect.
Hi @sidharth72
I am not sure if you are aware of these available options:
-endpointing
- https://developers.deepgram.com/docs/endpointing
utternace_end_ms
- https://developers.deepgram.com/docs/understanding-end-of-speech-detection
Those don't meet your needs and If you are proposing something else entirely, could you explain in greater detail what you are looking for? Something closer to a functional spec would be nice as I am not sure what you are trying to get at. You could drop it here in this issue or link to a Google Doc.
Thank You. I just found that it is possible to combine UtteranceEnd and Endpointing to detect End of Speech efficiently.
All good! Glad you have a solution!