OpenVoiceChat
OpenVoiceChat copied to clipboard
Have a natural voice conversation with an LLM
Repeated complex jumbled code.
https://www.twilio.com/docs/voice/media-streams/websocket-messages#send-a-mark-message Is the way twilio synchronizes the audio pipeline.
Where should the buffering happen? When it is on device, buffering happens in BaseMouth. When it is on web, it should happen at the client. When it is on call...
There should be an audio handler that handles audio input and output. Having separate listener and player don't make sense. Also listening, listening for interruption should be states instead of...
Audio is converted from format to format a lot over the codebase. This should be managed and documented reasonably.
RASA chatbot could be a good use case as well
Ideally something like the logging module from python is used or something
Should drop support for some models at some point. Should add claude to llm but remove llama_cpp. Ollama should be the default for local models. Maybe figure out hf. Should...