Voice-Pro is hailed as the best gradio WebUI for transcription, translation, and text-to-speech. This tool offers various features like real-time transcription, translation, and batch mode, along with a YouTube downloader and vocal remover. Unique functionalities include the STT support with Whisper, Faster-Whisper, and whisper-timestamped, as well as the Translator using Google Translator. Notably, the TTS feature provides Edge-TTS and F5-TTS with zero-shot voice cloning support, along with free Celeb voices for podcast creation. The Studio tab integrates all tools seamlessly, including YouTube downloader, noise removal, subtitles, translation, and TTS, making it a comprehensive solution for multimedia content processing.
https://github.com/abus-aikorea/voice-pro