← all repositories

vndee/local-talking-llm

A voice assistant that runs locally using Whisper for speech recognition, Ollama for LLM inference, and ChatterBox TTS for speech synthesis.

local-talking-llm
Velocity · 7d
+1.1
★ / day
Trend
steady
star history

This project builds a fully offline voice assistant similar to JARVIS from Iron Man. It combines Whisper for converting speech to text, Ollama for running large language models locally without internet, and ChatterBox TTS for generating spoken responses with voice cloning and emotion control. Users can interact with the assistant through voice, and it operates entirely on the user’s own computer.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.