ollama-voice

Plug whisper audio transcription to a local ollama server and ouput tts audio responses

This is just a simple combination of three tools in offline mode:

• Speech recognition: whisper running local models in offline mode
• Large Language Mode: ollama running local models in offline mode
• Offline Text To Speech: pyttsx3

Prerequisites

whisper dependencies are setup to run on GPU so Install Cuda before running pip install.

Running

Install ollama and ensure server is started locally first (in WLS under windows) (e.g. curl https://ollama.ai/install.sh | sh)

Download a whisper model and place it in the whisper subfolder (e.g. e5b1a55b89/large-v3.pt)

Configure assistant.yaml settings. (It is setup to work in french with ollama mistral model by default...)

Run assistant.py

Todo

• Allow a full conversation with a "press to talk" function between requests
• Process ollama json responses in stream mode to generate voice at the end of each sentence.