abus-aikorea/voice-pro

Project overview

A Gradio web application combining speech recognition, multilingual translation, dubbing, text-to-speech, voice cloning, audio processing, video download, and vocal isolation. It targets creators and developers who need a unified voice-processing workflow.

Project type

Workflow · Audio & Speech

Use cases

Translation & Subtitles · Audio & Speech

Deployment

Refer to project documentation

License

GPL-3.0

Best for

• Developers and creators who need a combined Gradio WebUI for translation, dubbing, voice cloning, and audio processing tasks.

Key capabilities

• Provides speech recognition in the web application.
• Translates content across multiple languages as part of the application workflow.
• Provides multilingual dubbing through the web application.
• Offers text-to-speech using Edge-TTS and kokoro.
• Offers zero-shot voice cloning using E2-TTS, F5-TTS, and CosyVoice.
• Processes audio with Whisper.
• Downloads YouTube content for its processing workflow.
• Isolates vocals with Demucs.

Limitations and risks

• GPU availability, minimum hardware, database dependencies, external services, and model requirements are not documented.
• Deployment methods, local execution options, and detailed setup difficulty or instructions are not documented.

Getting started

• Setup difficulty and first success steps are currently undocumented. Users should verify hardware compatibility, particularly for GPU resources, before proceeding.

Evidence and sources

• README: 🎙️ An AI-powered web application for speech recognition, translation, and dubbing
• GitHub project description: Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube downloa…
• Release: v4.0.0
• README: platforms: Windows

Reviewed at: 2026-07-14T23:33:58Z