generated from PeoplePlusAI/the-project-template
-
Notifications
You must be signed in to change notification settings - Fork 5
Open
Description
Description
Right now we are chunking 5 seconds of audio and sending it to backend. Instead of this use something like livekit to stream the audio and process the response properly. We will handle the chunking part in the backend.
Expected Behavior
- Stream audio to backend
- Backend will then preprocess the audio based on the ASR API's capabilities
Current Behavior
- 5 seconds of audio are sent to the backend
- And backend process this 5 seconds of audio irrespective of the chunking mechanism used in the ASR API