Tools
huggingface/speech-to-speech Posts the Day's Highest Star Velocity as a Fully Swappable Local Voice Pipeline
Hugging Face's speech-to-speech gained +1,342 stars today — the largest single-day velocity across all trending Python repos, roughly double the next — reaching 9,740 stars and 1,182 forks. It exposes a VAD → STT → LLM → TTS pipeline behind an OpenAI Realtime-compatible WebSocket API with every stage swappable: Parakeet TDT as default STT (Whisper and Paraformer alternatives), Qwen3-TTS as default TTS (Kokoro, Pocket TTS, ChatTTS, MMS TTS alternatives), Silero VAD v5, and LLM via OpenAI-compatible endpoint, Transformers, or MLX-LM on Apple Silicon. It is already in production on Reachy Mini robots. Note the repo dates to 2024-08-07 — this is a surge on an existing project, not a launch.
↳ Follow the thread