Fabric 1.0 allows you to generate realistic lip-synced videos by combining an image with audio. This tool is designed for creators, teams, and professionals who want to bring static talking head characters to life using generative video.
Limitations
Uses AI Credit for each generation.
Up to 30 seconds of length per clip.
How to Generate a Lip-Synced Video
Open Editor > Video > Generate Tab > Talking Video > VEED Fabric 1.0 model, or click here.
Select generate or upload a character image.
Add audio by uploading a file, recording with your microphone, or generating text-to-speech using an AI voice(30 seconds maximum length).
Click Generate to create your lip-synced video.
Character options:
Upload your own image
Generate an image using AI
Choose from VEED’s character library
Audio options:
All audio options have a maximum length of 30 seconds.
Record with your microphone
Upload an audio file
Use AI voice (text-to-speech)
Important Notes
Lip-sync quality works best with clear audio input.
Multiple short clips can be generated and combined for longer videos.
Works with various character styles (realistic, illustrated, animated, etc.).
FAQ
Q: How can I create videos longer than 10 seconds?
A subscription with credits is required for 30-second videos.
Q: Is there an API available for Fabric?
Yes, an API is available for Fabric that you can access here. It is available through Fal. It is not part of our pricing plans.