Video generation
Available now

Veed Fabric 1.0

by Veed

Veed's talking‑video model.
One still plus one audio file becomes a talking video with synced lips, head, body, and hand motion.

Veed Fabric 1.0

by Veed

Key features

Technical specifications

1 image + 1 audio

JPG, PNG, WebP, GIF + MP3, WAV, M4A

480p or 720p

Two output tiers

5 ratios

16:9, 4:3, 1:1, 3:4, 9:16

Up to 5 min

Per generation

Use cases

Talking-avatar social content

Generate talking-head clips for Instagram, TikTok, LinkedIn, and Shorts from one image and a voice track. No studio shoot needed.

Ads and explainers

Use a brand character or mascot still as the speaker for ads, product explainers, and tutorials. Visual identity stays consistent.

Multilingual content localization

Generate the same talking video in multiple languages by swapping the audio track, lip-sync follows the new language automatically.

Stylized character speech

Animate illustrations, anime, clay-style mascots, or 3D renders speaking, not just realistic portraits. Fits branded and entertainment work.

Prompt examples

Talking-head ad

Animate this character portrait speaking the attached audio track, neutral background, mid shot, 720p, 30 seconds

Edit prompt

Stylized mascot

Make this illustrated mascot speak the attached voiceover, expressive lip and head motion, full body in frame, 60 seconds

Edit prompt

Localized explainer

Generate a talking video of this character delivering the attached Spanish voiceover, accurate lip-sync, soft natural body motion, 90 seconds

Edit prompt

Overview

Veed Fabric 1.0 is Veed's talking-video model, a different shape from a standard lip-sync model. Instead of starting from existing footage and re-syncing the mouth, Fabric takes a single still image plus an audio file and generates the entire talking video from scratch, with lips, head, body, and hand motion all driven by the audio. It accepts realistic photos, illustrations, anime, 3D renders, and stylized mascots, supports any language via the input audio, and runs up to 5 minutes per generation, long enough to cover full explainers and ad reads in a single pass.

ByteDance's OmniHuman 2.0 works from the same two inputs, one photo and one audio track, and reads the tone and emotion of the track for takes up to five minutes. Both are live on Morphic, so you can run the same photo and track through each and keep the better take.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$19/ month
billed as $0 per year

2400 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is Veed Fabric?
Veed Fabric 1.0 is Veed's talking-video model. It takes a single still image and an audio file, and generates a video of the subject speaking the audio with synced lip, head, body, and hand motion.
How is Veed Fabric different from a normal lip-sync model?
Most lip-sync models start from existing video and re-sync the mouth to new audio. Fabric starts from a single still image and generates the entire talking video from scratch, useful when you don't have source footage of the character at all.
What styles does Veed Fabric support?
Realistic photos, illustrations, 3D renders, anime, clay-style mascots, and other stylized art. The same model handles a portrait or a cartoon character.
What languages does Veed Fabric support?
Any language. Fabric is driven by the input audio, swap the voice track and the lip-sync follows the new language, useful for content localization from one source image.
How long can a Veed Fabric clip be?
Up to 5 minutes per generation, well beyond the typical 8–20 second ceiling for talking-avatar models, long enough to cover full explainers, ads, and short tutorials in one run.
How do I use Veed Fabric on Morphic?
Open Copilot, attach a character image and a voice track, and pick Veed Fabric. For talking-head social content, ads, or multilingual explainers where you only have a still and an audio file, Fabric is the right pick.

Other models

Explore the rest of the Morphic model catalog.

See all models →

FLUX Video Upscale

Black Forest Labs

Black Forest Labs' video upscaler. Up to 4K, with fine detail rebuilt and the sound kept.

FLUX 3 Max

fal.ai

fal's post-trained FLUX 3. Tuned to follow the script, built for speed.

Krea 3

Krea AI

Krea's fast image editing model. Combine up to 4 images in one edit.

OmniHuman 2.0

ByteDance

ByteDance's audio-driven human video model. One photo, one track, five minutes in one take.