realtime speech ⇄ text, 音を字に — wire mic → STT → translate → speech as an on-device voice graph that spans your devices over WebRTC. Runs in the browser (transformers.js/ONNX/WebGPU); no API keys, nothing leaves the device by default.
Model-agnostic multi-modality generation server with plugin discovery: OpenAI-compatible TTS, embeddings, and image generation. Drop a Python file in ~/.muse/models/ to add a backend.
Native Text-to-Speech plugin for Tauri 2.x applications. Provides cross-platform TTS functionality for desktop (Windows, macOS, Linux) and mobile (iOS, Android).
Any-TTS is an open-source, high-quality text-to-speech (TTS) toolkit for generating natural-sounding speech from text—featuring easy setup, flexible voices/languages, and developer-friendly APIs for apps, bots, and automation.