Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A real-time speech-to-speech chatbot powered by Whisper Small, Llama 3.2, and Kokoro-82M.
| Date | Stars |
|---|---|
| 2026-07-24 | 251 |
| 2026-07-25 | 251 |
| 2026-07-28 | 252 |
| 2026-07-30 | 253 |
| 2026-08-06 | 253 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Weebo A real-time speech-to-speech chatbot powered by Whisper Small, Llama 3.2, and Kokoro-82M. Works on Apple Silicon. Learn more [here](https://amanvir.com/weebo). ## Features - Continuous speech recognition using Whisper MLX - Natural language responses via Llama - Real-time text-to-speech synthesis with Kokoro-82M - Support for different voices - Streaming response generation ## Setup Download required models: - [`kokoro-v0_19.onnx`](https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files/kokoro-v0_19.onnx) (TTS model): `wget https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files/kokoro-v0_19.onnx` - Pull the llama3.2 model using Ollama: `ollama pull llama3.2` - for Mac: `brew install espeak-ng` - for Mac: `export ESPEAK_DATA_PATH=/opt/homebrew/share/espeak-ng-data` ## Usage Run the chatbot: ```bash uv run --python 3.12 --with-requirements requirements.txt main.py ``` The program will start listening for voice input. Speak naturally and wait for a brief pause - the bot will respond with synthesized speech. Press Ctrl+C to stop. Alternatively, create an environment and install the requirements: ```bash python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt python main.py ```
Excerpt of 1,278 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2d550d65ed3ff854, topic:whisper, readme:speech recognition, readme:text-to-speech
matched fp:2d550d65ed3ff854, topic:llama