ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation Paper β’ 2607.08741 β’ Published Jul 9 β’ 12
Runtime error Agents 82 Vocal Separation SOTA π€ 82 Separate vocals and music from any audio file or YouTube video
Running on Zero MCP Featured 46 Auffusion π» 46 Audio Gen, Audio Style Transfer and Audio InPainting
Running on Zero Agents Featured 983 MMAudio β generating synchronized audio from video/text π 983 Generate synchronized audio for videos or from text prompts
Running on Zero MCP Featured 154 KDTalker π 154 Generate a talking-head video from a photo and audio
Running on Zero Agents Featured 5.08k MusicGen π΅ 5.08k Generate music from a text description and optional melody
Running Agents Featured 623 ElevenLabs TTS π£ 623 Generate spoken audio from text using selectable voices