URL of the person/avatar image
Text description for the video generation
Choose audio source type
Disabled
Whether to enhance/improve the prompt automatically
Random seed for reproducible generation
Result
Your generated video will appear here
Configure your parameters and click generate to get started
Higgsfield Speak
$0.25
Per generation
Higgsfield Speak is an AI lip-sync model that animates faces in images to speak along with audio. Create realistic talking head videos from a single image and audio file.
Lip Sync Animation
Realistic lip synchronization that matches audio speech perfectly.
Single Image Input
Only requires one face image to create animated talking videos.
Audio Support
Upload any audio file to drive the lip movements of your character.
Quality Modes
Choose between Basic ($0.25) and High ($0.35) quality output.