Multi-speaker lip-sync with 'Detect Active Speaker'
Sync
Demo summary
The demonstration shows how to enable the 'detect active speaker' setting in Sync to automatically identify and sync only the person currently talking in a multi-person frame.
Step-by-step
- Go into the Settings menu
- Turn on the Detect Active Speaker toggle
Tips
- Use this feature when editing podcasts, interviews, or videos with multiple speakers
- Test the feature on your specific footage as performance may vary depending on the scene
Highlights
“it's a pretty huge feature if you're, you know, editing podcasts, interviews, or multispeaker videos”
All demos from “AI lipsync with Sync”
- 1:220:39Translate and lip-sync video with Sync.soThe creator demonstrates the Sync.so web interface by creating a new project, uploading a video, and pasting translated Spanish text to generate a lip-synced output.Sync.So· AI Lip Sync Generator
- 2:111:30Advanced voice cloning and obstruction detection in Sync.soThe demo shows how to upload an audio sample for voice cloning and toggle the 'detect obstructions' setting to maintain lip-sync accuracy when a hand covers the mouth.Sync.So· AI Lip Sync Generator
- 4:460:35Installing and using the Sync custom node in ComfyUISebastian walks through installing the Sync custom node via Git URL in ComfyUI and setting up a workflow with video/audio input nodes and the Sync generate node.ComfyUI· AI Lip Sync Generator
- 5:291:09Combining image-to-video models with Sync in ComfyUIThe video demonstrates a complex workflow using Krea.ai to transform a shot into a cinematic style before passing the generated video into Sync for final lip-syncing.ComfyUI· AI Lip Sync Generator
- 7:070:23Multi-speaker lip-sync with 'Detect Active Speaker'CurrentThe demonstration shows how to enable the 'detect active speaker' setting in Sync to automatically identify and sync only the person currently talking in a multi-person frame.Sync· AI Lip Sync Generator
- Watch “AI lipsync with Sync” →
AI Lip Sync Generator
- 7:070:23Multi-speaker lip-sync with 'Detect Active Speaker'CurrentThe demonstration shows how to enable the 'detect active speaker' setting in Sync to automatically identify and sync only the person currently talking in a multi-person frame.Sebastian Kamph