Voice-Pro by ABUS-AIKOREA is a powerful AI-driven desktop web application designed for multimedia content creation and processing. It integrates YouTube video downloading, voice separation, advanced speech recognition, multilingual translation, and text-to-speech capabilities. The tool supports zero-shot voice cloning and multilingual TTS, offering a comprehensive solution for content creators, researchers, and multilingual professionals. Utilizing core technologies like Whisper series, F5-TTS, E2-TTS, and CosyVoice, it provides high-quality speech recognition, cloning, and translation services.
pyVideoTrans is an open-source tool dedicated to video translation, audio transcription, AI dubbing, and subtitle generation. It seamlessly converts videos into another language using an automated pipeline: Speech Recognition (ASR), Subtitle Translation, Speech Synthesis (TTS), and video-audio synchronization. Key features include speaker diarization and zero-shot voice cloning. It offers extensive compatibility with both local offline models and mainstream cloud APIs. Featuring an interactive GUI for manual proofreading and a headless CLI for batch deployment, it provides a highly flexible solution for multimedia localization.