VoiceStudio, an open-source local ElevenLabs alternative, trends on GitHub
VoiceStudio is an open-source, fully local voice tool that appeared on GitHub Trending's Python list. Its README describes voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation, claims support for 646 languages, and says the default engine is k2-fsa/OmniVoice with other engines selectable. The app ships as an Electron desktop client with a local API and MCP integration for agents, is licensed AGPL-3.0, and notes that model weights, voices and generated output carry separate conditions.
For developers who want voice cloning and transcription to run on their own hardware instead of a cloud service, the project offers a packaged desktop option with a local API and MCP; its feature set and 646-language claim come from the project itself and have not been independently verified.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
VoiceStudio
Open-source voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.