01117 GitHub stars
02Advanced Speech Synthesis featuring a rich voice library, real-time preview, voice cloning (CosyVoice2, GPTSoVITS), and emotion-aware synthesis.
03Flexible Preview and Debugging tools for efficient configuration adjustments and quality assurance throughout the creation process.
04Draft Editing capabilities with multi-track control for visuals, audio, and subtitles, and customizable export options.
05Multilingual Translation with support for various providers (e.g., OpenAI, Gemini, DashScope) and custom models.
06Accurate Subtitle Recognition with multi-provider support (e.g., Srt, Capcut, FasterWhisper) and speaker/emotion detection.