Voice-Pro
A local AI dubbing and voice cloning app with Whisper transcription and a browser interface that requires internet access.
Alternative to:
Voice-Pro is a locally run speech processing and dubbing app for creators working with recordings or multilingual video. Its Gradio browser interface brings audio preparation, transcription and speech generation into one workspace. Internet access is required.
- Audio preparation: Download YouTube videos and extract their audio with yt-dlp, then separate vocals with Demucs.
- Transcription and translation: Transcribe speech with Whisper, Faster-Whisper or Whisper-Timestamped, and use live speech recognition and multilingual translation.
- Voice cloning: Generate speech from reference audio with F5-TTS, E2-TTS or CosyVoice without training a separate voice model; Fun-CosyVoice3 supports Korean.
- Text-to-speech: Produce spoken audio with kokoro or Edge-TTS, with optional Azure TTS available using your own service credentials.
Translation uses Deep-Translator, with Azure Translator available as an optional external service requiring your own credentials. The app runs locally, but it isn't an offline tool.
Voice-Pro is open source under GPL-3.0. Supported platforms include Windows, Linux and macOS on Apple Silicon. Its stated hardware requirements include an NVIDIA GPU with at least 4GB of VRAM (8GB preferred), 4GB of RAM and 20GB of free storage.