linyiLYi/voice-assistant

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1323 stars · 212 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A simple single-script Python demo of a local voice assistant that uses Whisper (via Apple MLX) for speech recognition and a local Yi large language model (GGUF via llama-cpp-python) to generate spoken responses. It is a toy project tested on macOS, not a production-ready assistant.

Use cases

• run a voice assistant fully locally on my mac
• talk to a local LLM with my microphone
• demo whisper speech recognition with a local chat model
• learn how to build a simple voice assistant in python
• offline voice chat without cloud APIs

When to choose

• you want a minimal, readable example of wiring Whisper + a local LLM together
• you are on macOS with Apple Silicon and want MLX/Metal acceleration
• you need a learning or prototyping starting point for voice assistants

When to avoid

• you need a production voice assistant with wake words, streaming, or multi-turn memory
• you need first-class Windows or Linux support (the readme only suggests workarounds)
• you want a polished installable application rather than a single script

Facets

application · maturity experimental

speech-recognition llm-inference audio-processing chatbot artificial-intelligence large-language-models speech-processing python voice-assistant whisper local-llm mlx yi-model toy-demo gguf llama-cpp voice-assistants macos desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="linyiLYi/voice-assistant")