Open Source Voice AI tools

Voicebox is an open-source desktop app for voice cloning and TTS that clones voices from short samples, supports WAV/MP3/FLAC/WEBM and mic capture, multi-voice timeline editing with effects, local or remote GPU inference, Whisper STT, and API integration.

Open Voice OS is an open-source, community-driven voice AI platform for building customizable assistants across Raspberry Pi, embedded devices, Linux desktops, and Docker. It provides plugin-based STT/TTS, configurable wake words, extensible skills, and privacy-focused self-hosting.

Whisper is an AI-powered speech recognition tool for multilingual speech recognition, speech translation, and spoken language identification.

Supertonic is a lightning-fast, on-device text-to-speech (TTS) system built for local inference using ONNX Runtime, supporting 31 languages and offering a compact, open-weight model for edge deployment.

MimikaStudio is a macOS (Apple Silicon) local-first voice cloning and TTS app that creates voices from short samples, generates long-form audiobooks with chapter markers and highlighting, runs on-device with multiple engines, model manager, REST API and automation.