huggingface/speech-to-speech

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A modular voice agent pipeline that chains voice activity detection, speech recognition, a language model and speech synthesis. It exposes OpenAI Realtime events over WebSocket and WebRTC, and every component can be swapped, including a locally run LLM.

How it helps ATF

Only loosely related. It could be a reference if voice input were considered for the AI assistant in ATF Works, since each speech and language model stage can be swapped or run locally.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• LiamGvchi/gc-minimal-zine-poster
  GC Minimal Zine Poster is a Codex skill that turns a theme, sentence, object, mood or photo into a sparse paper-texture editorial poster, an image prompt or a reusable visual system.
• img2threejs/img2threejs
  Rebuilds the object in a reference image as a procedural Three.js model made only of code, instead of photogrammetry, mesh extraction or downloaded art packs. The models are quality-gated and ready for animation.
• debpalash/VoiceStudio
  VoiceStudio is an open-source app that runs locally for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages. It also offers a local API and MCP for agents.
• bradautomates/claude-video
  A skill that lets Claude answer questions about a video from a URL or local path. It uses captions or, as a fallback, a Whisper transcript with timestamps, extracts frames, and passes them to Claude as images.
• crmne/spotifast
  Spotifast is a native Spotify client written in Rust with egui that plays music through librespot and appears as a Spotify Connect device. It runs on Linux, macOS and Windows, and playback needs Spotify Premium.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.