Files
research_and_development/ai-conversation
2025-07-26 17:15:14 -07:00
..
2025-07-13 11:52:09 -07:00
2025-07-13 11:52:09 -07:00
2025-07-13 11:52:09 -07:00
2025-07-13 11:52:09 -07:00
2025-07-26 17:15:14 -07:00

Conversation

This proof of concept is for implementing conversational loop with AI at a low level.

  • Capture audio
  • Use deepgram for live transcription
  • Detect final speech/turn detection
  • AI answer -> text
  • Text -> generated voice with deepgram
  • Playback on client side

Requirements

Platform: the project is meant for Linux, specifically Ubuntu desktop.

Implementation

The loop should be as follows:

  • create the thread that manages the deepgram websocket client
  • grab audio and send over to other thread to process & send
  • stream pcm packets over the websocket connection
  • print inbound messages from websocket connection to stdout
  • signal in stdout when there is a "final message", which signifies "turn detection"

Open questions

  1. Can deepgram websocket stream take any format? raw pcm? Answer here
  2. Consider using Golang to interop with c, whereby the golang uses deepgram sdk, and the c library for alsa.