Voice-Pro
lastmod 2024-12-11created 2024-12-112 edits
Voice-Pro is a Gradio WebUI that supports speech recognition, translation, and speech synthesis.
Key features
- Zero-shot voice cloning. Only a 15-second voice sample is needed. Provides 50+ celebrity voices
- YouTube audio download
- Vocal separation
- Multilingual text-to-speech (Edge-TTS, F5-TTS)
- Multilingual translation
- Supports various Whisper engines (Whisper, Faster-Whisper, Whisper-Timestamped)