GitHub radar
VoiceStudio: clone voices, dub videos and transcribe speech locally
A free app that runs on your own computer: it clones voices, dubs videos into another language, takes dictation and narrates text in 646 languages — no accounts, no subscriptions.
A local voice studio that clones and designs voices, dubs videos, transcribes speech and narrates text in 646 languages.
When it helps
Useful when you want to dub or translate a video, clone a voice, or transcribe a recording without paying for cloud. If you need top speed on heavy jobs and have no GPU, it'll run slower than a paid cloud service.
Pros
- Runs on a regular CPU, no GPU required
- No accounts or keys, your data stays on your device
- Dozens of engines to pick from — speed or quality
- Free, with no paid cloud behind it
Cons
- Without a GPU it's noticeably slower than cloud services
- Phone versions are still early preview releases
How to set it up — step by step
- 1Open your coding agent (Claude Code, Codex) in your project folder.
- 2Send the agent the text from the block below.
- 3Let the agent install VoiceStudio and wait for confirmation that it works.
- 4Open the voice cloning workspace and pick or record a sample voice.
- 5Ask the agent to dub a short video into another language as a test.
- 6Listen to the result and check it sounds like the original.
Text for your agent
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install VoiceStudio from https://github.com/debpalash/VoiceStudio — follow the README, no accounts or API keys needed. After it's installed, show me how to clone a voice or dub a short video into another language.
Light: no GPU needed, runs fine on a regular CPU too, just slower. Apple Silicon, NVIDIA and AMD get acceleration. Available for Mac, Windows, Linux, and as a preview app for phones.
Open on GitHub▌ More finds