Voice-Pro unifies TTS, voice cloning, audio tools
Voice-Pro is an open-source Python application that integrates leading text-to-speech and audio editing tools into a streamlined Gradio WebUI. Developed by abus-aikorea, the project supports popular TTS engines like Edge-TTS and Kokoro alongside zero-shot voice cloning models including E2-TTS, F5-TTS, and CosyVoice. In addition to speech synthesis, Voice-Pro packs Whisper transcription, YouTube audio extraction, Demucs vocal isolation, RVC voice conversion, and multilingual translation into an all-in-one local production suite.
Voice-Pro solves the fragmentation problem in open-source AI audio by combining isolated TTS, vocal separation, and voice cloning models into a unified local workflow. It integrates state-of-the-art models such as Kokoro, F5-TTS, E2-TTS, and CosyVoice alongside end-to-end processing features like YouTube downloading, Demucs vocal isolation, Whisper transcription, and RVC voice conversion. This provides an all-in-one local suite for content creators, localization teams, and audio developers.
DISCOVERED
1d ago
2026-08-01
PUBLISHED
1d ago
2026-08-01
RELEVANCE