LyricMotion AI
✦ Open Source Wav2Lip + Whisper
✦ 100% Free ✦ Self-Hosted AI ✦ Open Source

AI Lip-Sync Videos
Completely Free

Upload a song + photo or video, pick a style, and generate stunning lip-sync music videos powered by open-source AI. No subscription, no limits.

🎵
Audio Sync
Whisper-powered transcription, auto lyric sync and subtitle generation
👄
Lip Sync AI
Wav2Lip & SadTalker animate any face in photos or videos
🎨
Style Engine
Anime, Cinematic, Retro & more via open-source model filters
⚡
Zero Cost
No paid APIs, no subscriptions. Self-host the full AI pipeline
Powered by open-source AI
Wav2Lip SadTalker Whisper FFmpeg MediaPipe AnimeGAN OpenCV Stable Diffusion RNNoise Python FastAPI
How it works
📤
1. Upload
Song + photo or video
🎨
2. Style
Pick visual style & settings
🤖
3. Generate
AI renders lip-sync video
💾
4. Download
Export MP4 in HD quality
Dashboard
Manage your lip-sync video projects
🎬
0
Total Projects
✅
0
Videos Generated
⏱
0:00
Total Duration
⚡
∞
Free Credits
Recent Projects
🎬
No projects yet
Create your first AI lip-sync video
Create Project
Build your AI lip-sync video
Step 1 / 3
🎵 Audio / Song
🎵
Drop MP3 / WAV here
or click to browse
👤 Character Photo / Video
🖼️
Drop Photo or Video
JPG / PNG / WEBP / MP4 / MOV
AI detects & animates the face
🎙️
Upload voice recording
RNNoise denoising • No ElevenLabs needed
🎨 Visual Style
📐 Aspect Ratio
📝 Project Info
⏱ Duration
✨ Bonus Features
📋 Summary
⚙️ Processing Pipeline
🎵
Preview Frame
🎤 Sample subtitle text appears here...
0:42 / 3:24
🔊
Sample Project
Realistic · 16:9 · 3:24
Audio Track
Lip Sync
Subtitles
Settings
Configure the AI pipeline and app preferences
AI Model Configuration
GPU Acceleration
CUDA/ROCm — CPU fallback if unavailable
Larger = better transcription, slower processing
SadTalker
3D face animation for images
AnimeGAN
Anime & cartoon style transfer
Stable Diffusion
Background generation (needs 8GB+ RAM)