VoiceStudio

VoiceStudio

VoiceStudio (formerly OmniVoice Studio) is an open-source desktop app, launched in 2026 and built by Palash Debnath in India, that runs voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation entirely on your own computer. It positions itself as a local alternative to cloud voice platforms: no account, no API key and no usage limits, and audio stays on the machine. The project is published on GitHub under AGPL-3.0, has more than 50,000 stars and says it supports 646 languages.

Key Features

• Voice cloning: Clones a voice from about three seconds of audio, for use only with the owner's consent.
• Voice design: Creates a new voice from a text description.
• Video dubbing: Translates and re-voices a video into another language while keeping the timing.
• Transcription and dictation: Turns audio into searchable text and supports real-time dictation.
• Stories and audiobooks: Casts different voices across a script and turns a book into chaptered audio.
• Local API: Exposes the engines through a local API, with Windows, macOS, Linux and Docker builds.

Use Cases

• Creators: Voice-overs, dubbing and audiobooks without per-character billing.
• Privacy-sensitive teams: Voice work that cannot be uploaded to a third-party cloud.
• Developers: Testing open TTS and speech recognition engines through one local interface.

Getting Started

VoiceStudio is free to download. A paid Pro build with a commercial license is also available: https://voicestudio.sh/