bytedance/MegaTTS3

MegaTTS3: speech-to-text aligner and TTS model with voice cloning, supports Chinese and English, runs locally

View on index · View in 3D Map

Related repos

• open source text-to-speech model built by inverting Whisper, supports voice cloning and multilingual output
• LLM-powered text-to-speech with voice cloning and bilingual support
• zero-shot text-to-speech with voice cloning for English and Chinese
• Text-to-speech on CPUs with voice cloning
• simple voice cloning tool with multi-language support
• Run speech-to-text and translation with a Whisper-powered API that supports multiple engines and formats
• offline speech-to-text API for many languages, runs on lots of devices and platforms
• self-hosted lightweight text-to-speech server with web UI and GPU support
• Text-to-speech with voice cloning and multilingual support
• Open-source multilingual TTS with voice cloning