100% Local • Privacy First

Your Voice,Understood.

A real-time voice AI assistant that runs entirely on your machine. No cloud. No latency. No compromises.

Listening...

Designed for the future.

Built with the technologies that matter.

Real-Time Processing

Whisper Turbo MLX delivers blazing fast speech-to-text on Apple Silicon. No waiting, no buffering.

Local LLM

Powered by Llama 3.1 running locally via llama.cpp. Your conversations never leave your device.

Zero Dependencies

No API keys. No cloud services. No internet required. Pure, standalone AI.

Apple Silicon Optimized

MLX framework ensures maximum performance on M1, M2, M3, and M4 chips.

How it works.

Three steps. One seamless experience.

01

Speak

Just talk naturally. TARS captures your voice in real-time using your microphone.

02

Understand

Whisper transcribes your speech instantly. The LLM comprehends context and intent.

03

Respond

Natural speech synthesis delivers the response. A fluid conversation, powered by AI.

Built with precision.

A carefully crafted architecture for voice AI.

Input
🎤PyAudioMicrophone Capture
Transcription
Whisper Turbo MLXSpeech-to-Text
Intelligence
Llama 3.1 8BLocal LLM via llama.cpp
Output
🔊pyttsx3Text-to-Speech

Get started in minutes.

Clone, install, run. It's that simple.

Terminal
# Clone the repository
$ git clone https://github.com/yourusername/tars.git
$ cd tars

# Install dependencies
$ pip install -r requirements.txt

# Download a model (example: Llama 3.1 8B)
$ mkdir -p models && cd models
$ wget https://huggingface.co/...

# Run TARS
$ python index.py

Ready to talk?

Experience the future of voice AI. Locally.

View on GitHub