A UI software based on ChatTTS, ChatTTS can be used for dialogue tasks of large language model assistants, dialogue speech generation, video introductions, voice synthesis of educational and training content, etc. Through training with a large and diverse dataset, ChatTTS ensures the naturalness of synthesized speech.
Software Features
Automatic video translation: Integrated faster-whisper model/and support for custom huggingface models. Also integrated batch speech-to-subtitle, batch subtitle translation, batch voice-over tools.
Multiple voice-over and translation channels: Voice-over: edgeTTS|AzureTTS|OpenAiTTS|Elevenlabs|clone-voice|GPT-SoVITS. Translation: Google|ChatGPT|DeepL|Gemini|Mircosoft|Baidu|Tencent|Local models
Fully offline: Replace translation channels with local models, replace voice-over channels with clone-voice, to achieve completely offline video translation.
Free + Open Source: Code openly available on GitHub for review, free with no functional limitations, no hidden charges. Open source license GPL-v3.
Project Links
Download link: https://pyvideotrans.com/
Demo: https://chattts.com/#Demo
Open source link: https://github.com/jianchang512/ChatTTS-ui
Voice preview: https://github.com/jianchang512/ChatTTS-ui/assets/3378335/03cf1c0f-0245-44b5-8007-370d9db2bda8