AI Agent Skills

Code. Music. Live.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.

Generate a controlled local narration workflow with auditions, version tracking, and subtitle-ready final audio.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning