Repolode
Submit
abus-aikorea

abus-aikorea/voice-pro

Windows-focused Gradio web app bundling text-to-speech, voice cloning, Whisper transcription, YouTube download, vocal separation and translation for dubbing.

Open-source alternative to:ElevenLabs

View on GitHubWebsite
Stars
13,226
Forks
1,909
Open issues
62
Last commit
3 months ago

What is it?

Voice-Pro is a Gradio-based web application for dubbing and subtitle work. It combines YouTube video download and audio extraction, Demucs-based voice separation, speech recognition with Whisper, Faster-Whisper and Whisper-Timestamped, and translation across 100+ languages through Deep-Translator, with optional Azure Translator.

For speech output, it offers text-to-speech through Edge-TTS and kokoro, and zero-shot voice cloning through F5-TTS, E2-TTS and CosyVoice. Work is organized into WebUI tabs: Dubbing Studio, Whisper Caption, Translate and Speech Generation.

The installer is designed for Windows with an NVIDIA GPU, and the project is licensed under GPL-3.0. The developer notes that ongoing development has paused, and Mac and Linux operation has not been verified.

Key features

  • 01Transcribes speech with Whisper, Faster-Whisper and Whisper-Timestamped
  • 02Generates speech with Edge-TTS, kokoro, and zero-shot cloning via F5-TTS, E2-TTS and CosyVoice
  • 03Downloads YouTube videos and extracts audio with yt-dlp
  • 04Separates vocals from music using Demucs
  • 05Translates subtitles in formats such as SRT and ASS

Use cases

  • Dubbing a YouTube video into another language with a cloned or preset voice
  • Generating subtitles for podcasts or videos with word-level timing
  • Isolating vocals from a song for karaoke or remixing
  • Translating subtitle files for multilingual distribution

Quick start

  1. 1

    Download or clone the repository from GitHub

  2. 2

    Run start.bat on Windows to install and launch the web app

    start.bat
  3. 3

    If problems occur, delete the installer_files folder and run start.bat again

    start.bat

Things to know

  • Built and tested for Windows with an NVIDIA GPU; macOS and Linux are not verified.
  • Development and updates are currently paused by the maintainer.
  • The project is licensed under GPL-3.0, a copyleft license that requires derivative works to remain open source.
  • Some optional features such as Azure TTS and Azure Translator need your own API keys.

Topics

#text-to-speech#voice-cloning#speech-recognition#whisper#gradio#subtitles#translation#dubbing#audiobook#faster-whisper

FAQ

What is voice-pro?
Windows-focused Gradio web app bundling text-to-speech, voice cloning, Whisper transcription, YouTube download, vocal separation and translation for dubbing. Voice-Pro is a Gradio-based web application for dubbing and subtitle work. It combines YouTube video download and audio extraction, Demucs-based voice separation, speech recognition with Whisper, Faster-Whisper and Whisper-Timestamped, and translation across 100+ languages through Deep-Translator, with optional Azure Translator.
Is voice-pro free to use? What license does it have?
voice-pro is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
Is voice-pro still maintained?
Updated within 6 months. The last commit to voice-pro was on Jul 13, 2026.
What can I use voice-pro for?
Dubbing a YouTube video into another language with a cloned or preset voice Generating subtitles for podcasts or videos with word-level timing Isolating vocals from a song for karaoke or remixing Translating subtitle files for multilingual distribution
How do I install voice-pro?
Download or clone the repository from GitHub Run start.bat on Windows to install and launch the web app: start.bat If problems occur, delete the installer_files folder and run start.bat again: start.bat
Where can I get voice-pro?
The source code and installation instructions are on GitHub: https://github.com/abus-aikorea/voice-pro

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects