RIFE Video Frame Interpolation
Smooth slow motion and 60fps conversion with RIFE 4.25
Browse and listen to open‑source TTS model samples
Generate audio from video, image, or text prompts
Generate audio from video and text prompts
Generate a talking‑head video from a face image and audio/text
Create a 3D avatar that speaks and reacts to your input
Talk to Gemma 4 face to face, with a 3D lip-synced avatar
Audio-driven talking-head video generation (Meituan LongCat)
Demo for DMOSpeech 2
Automatically add on-screen subs to your videos
Translate using Tencent's AngelSlim model