Download
Voice-Pro is the best gradio WebUI for transcription, translation and text-to-speech. It can be easily installed with one click. Create a virtual environment using Miniconda, running completely separate from the Windows system (fully portable). Supports real-time transcription and translation, as well as batch mode.
Features
- YouTube Downloader: You can download YouTube videos and extract the audio (mp3, wav, flac)
- Vocal Remover: Use MDX-Net supported in UVR5 and the Demucs engine developed by Meta for voice separation
- STT: Supports speech-to-text conversion with Whisper, Faster-Whisper, and whisper-timestamped
- Translator: Google Translator. Short text translation, subtitle file translation
- TTS: Text to Speech. Edge-TTS. E2 and F5-TTS that support zero-shot voice cloning
- We provide Celeb voices for free. Try creating your own podcast. You can check it in the F5-TTS tab
Project Samples
Categories
Text to SpeechLicense
MIT LicenseFollow Voice-Pro
Other Useful Business Software
Zenflow- The AI Workflow Engine for Software Devs
Zenflow is the AI workflow engine built for real teams. Parallel agents plan, code, test, and verify in one workflow. With spec-driven development and deep context, Zenflow turns requirements into production-ready output so teams ship faster and stay in flow.
Rate This Project
Login To Rate This Project
User Reviews
-
Tried Voice-Pro on my RTX 3080 desktop. The quality is truly excellent, and it includes voice cloning capabilities using F5-TTS and CosyVoice. The installation was very simple, and the usage is quite intuitive, so I think it's worth a try. Before installing this project, I checked their YouTube demo video, and I was able to achieve the same results on my desktop as shown in the demo. It offers transcription, translation, Edge-TTS and kokoro through the Gradio WebUI. It's a great tool for youtube creators. I hope you find it helpful.
