Fabric 1.0

By Veed

Fabric 1.0 is an image to video model that generates talking videos from one static image and an audio track. It analyzes audio waveforms to extract phoneme timing and maps it to facial keypoints, producing realistic lip sync, facial expressions, and body movement. Output is MP4 video at 480p or 720p, priced per second of output. Suited for talking avatar creation, video personalization, educational content, and marketing videos. A faster "Fabric 1.0 Fast" variant is also available for quicker turnaround at the same quality.

Video

Released: September 15, 2025

Overview

VEED Fabric 1.0 turns a single image and an audio clip into a realistic talking video, syncing lip movements, facial expressions, and body motion to the audio. Delivered via API with 480p and 720p output options for avatars and personalized video content.

📽️Image to video 🕺Avatar animation 🎥Video avatars 🎤Lip sync videos 🎥Personalized videos