We're excited to launch the Fabric 1.0 API, the world's first talking video model. Image-to-video AI has been advancing quickly, but Fabric 1.0 brings something new: faster generation, lower compute costs, and support for clips up to 5 minutes long. Our model generates video 60x cheaper than the average alternative and 7x faster.
Key takeaways:
- Fabric 1.0 is an image-to-video API that animates any image with a voice recording to produce a talking video
- The API generates video at 8 cents per second at 480p, making it suited for high-volume production pipelines
- Any image can be used as the visual input: photos, mascots, illustrations, 3D renders, and stylized artwork
- Fabric supports clips up to 5 minutes long, with 480p and 720p resolution options
- The model is available via VEED's API and accessible through fal.ai for developer integration
Instead of being limited to stock avatars, Fabric can animate any image and match it with speech, opening up far more creative possibilities. And now, it's available for developers and teams who want to generate AI videos at scale.
What is Fabric 1.0?
Fabric 1.0 is an image + audio to video model. You provide a picture and a voice recording, and the model produces a talking video. The audio drives not only lip movement but also head, body, and hand gestures, making the output natural and expressive.
- Make any static character talk: Upload a photo of your product, mascot, character or spokesperson and watch it speak. This opens up endless possibilities for branded content and unique personalities — explore more with AI avatars.
- Built for enterprise: Whether you’re launching a campaign, recording tutorials, or iterating on social ads, Fabric produces ready‑to‑share videos faster than human‑led production and without the need to film yourself.
- Infinite visual styles: Instead of being stuck with a few preset avatars, you can animate any illustration, clay figure or anime‑style drawing. The model interprets the artwork, matches lip movements to the audio and preserves the original look and feel.
Video API pricing: how Fabric compares
The most common question developers ask before integrating a video API is cost at scale. Platforms built around individual avatar sessions or monthly seat licenses get expensive fast once you push volume.
Fabric uses VEED's existing credit system and bills by resolution and duration:
At 8 cents per second, a 60-second video costs $4.80. A batch of 50 localized product videos at that length comes to $240 total. For comparison, dedicated AI avatar platforms typically charge multiples of that per minute, before factoring in seat fees or output limits. For teams running AI video generation at scale, that gap compounds quickly.
Why Fabric is different
The standard architecture for a talking video API locks you into a fixed avatar library. You pick from a list, record or type your script, and export. That works for simple use cases, but it breaks down when your brand requires a specific character, mascot, or spokesperson that does not exist in someone else's avatar catalog.
Fabric is built differently. The model accepts any image as the visual input and learns the character's features from that image rather than from a preset template. The practical result is that you can animate:
- A product mascot or illustrated character for branded content
- A custom spokesperson photo for localized ad campaigns
- An anime or clay-figure-style character for games or entertainment content
- A historical illustration or stylized artwork for educational video
The model preserves the look and feel of the original image while adding synchronized lip movement, head tilt, and body gesture. You are not mapping motion onto a generic base; the animation is derived from your specific input.
If you want to go further with customization, VEED's broader AI video tools give you editing, subtitles, and export controls on top of what Fabric generates.
Technical specs
Here are some more finer details of our model:
- Inputs: Image (jpg/jpeg/png) + audio (mp3/wav/m4a/aac) under 10 MB
- Max length: 5 minutes
- FPS: 25
- Aspect ratios: Standard formats including 16:9, 1:1, 9:16, and more
- Resolution: 480p and 720p (scaled appropriately for non-16:9 formats)
- Generation speed: ~1.5 minutes per 10s at 480p; ~5 minutes per 10s at 720p
The engine is powered by a Diffusion Transformer (DiT) trained on diverse datasets of talking people, which allows Fabric to deliver accurate lip sync and expressive motion across many different types of characters.
How the model works
- Upload an image: Fabric accepts photos, illustrations, 3D renders, and more.
- Add audio or text: Upload a recording or type a script. If you type, VEED's AI voice generator will narrate it.
- Generate your video: Fabric syncs the voice to your image and animates it with natural movements.
- Share anywhere: Export in vertical, square, or landscape formats for TikTok, Instagram, YouTube, ads, or presentations.
What to build with the Fabric video API
Fabric is designed for production volume. These are the use cases where the pricing model and flexibility make the most practical sense:
Localized ad creative at scale
Record a single script in multiple languages, pair each audio file with the same brand spokesperson image, and generate a complete set of localized videos in one batch. The per-second pricing keeps costs predictable regardless of language count.
Product explainer and tutorial video
Animate a product mascot or illustrated character to walk customers through a feature. No filming required. Combined with VEED's online video editor, you can add captions, overlays, and branding before export.
Social ad iteration
Run A/B tests across multiple spokesperson styles, image crops, or scripts without reshooting. Fabric's 5-minute clip limit and fast generation at 480p make quick iteration viable across a full ad set.
Training and onboarding content
Internal training videos benefit from consistent presenter visuals without requiring the presenter to be on camera for every update. Upload a photo, record the updated script, and regenerate only the sections that changed.
API documentation and integration
Fabric 1.0 is available on fal.ai. The endpoint accepts standard REST API calls and returns a video file URL on completion. Developer documentation covers:
- Authentication and API key setup
- Request body structure: image URL or base64, audio URL or base64, resolution and format parameters
- Response format and polling for async generation
- Rate limits and credit consumption per request
Access the full Fabric API documentation on fal.ai. For broader video editing capabilities beyond generation, the VEED API provides additional endpoints for editing, subtitles, and export.
Get Started
Fabric 1.0 API is available on fal.ai.
This release is just the beginning. We are already working on longer video support, higher resolutions, and even richer animation. It's game-changing for creators, marketers, and business owners!
