AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.085 per second of audio
VEED's talking avatar model that creates realistic speaking videos from a still image and up to 5 minutes of audio.
VEED Fabric 1.0 generates accurate mouth movements that match the audio.
The avatar's face responds to the emotion and emphasis in the audio.
VEED built Fabric 1.0 to be quick.
No complex setup or special photo requirements.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| VEED Fabric 1.0VEED | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Audio + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 720p | Up to 1080p | Up to 4K | Up to 720p |
| Length | — | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | — | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.085 per second of audio | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Aspect ratios | Sound |
|---|---|---|---|---|
| Talking photo | Audio, First frame | 480p, 720p | Follows the input | None |
$0/ month
$19/ month
$59/ month
$199/ month
VEED Fabric 1.0 was built for speed and cost. It generates realistic talking videos at a fraction of what traditional production costs. That speed unlocks workflows for people who need quick video turnaround without equipment or crews.
VEED Fabric 1.0 generates accurate mouth movements that match the audio. Lip movements sync to phonemes, and the mouth shapes feel natural. That credibility is critical for product demos, testimonials, and marketing.
The avatar's face responds to the emotion and emphasis in the audio. A question prompt gets raised eyebrows. A positive statement brings a slight smile. Subtle expressions make the avatar feel like a real person speaking.
VEED built Fabric 1.0 to be quick. The entire process from photo and audio to finished video happens in seconds, not minutes. That speed makes iteration practical for creators testing messages or content variations.
No complex setup or special photo requirements. A clear photo and audio are enough. No need to crop, edit, or prepare extensively beforehand.
Professional headshots are ideal, but not required. Phone photos work. Stock photos work. Any clear, well-lit image of a face gets good results.
VEED Fabric 1.0 is a transform model: provide a photo and audio, and Craze generates the animated video.
VEED Fabric 1.0 works well on photos where the face is clearly visible, well-lit, and roughly centered. Extreme angles or very distant shots may need cropping or editing before generation.
The speed comes from VEED's optimization for talking-head video. In Craze, you can generate a 60-second avatar video and review it quickly, which makes iteration and A/B testing practical for creators testing messages.
VEED Fabric 1.0 is priced by the length of your audio at $0.085 per second of audio. A 30-second voiceover costs less than a 1-minute video. Pricing scales linearly with audio duration. Use the cost calculator on this page for exact estimates.
Photo resolution, video quality, and aspect ratio don't affect the price. Only the duration of the audio matters.
Marketers and social media managers need talking videos fast. VEED Fabric 1.0 generates finished videos in seconds, making it practical for testing messages or responding to trends.
Founders, freelancers, and solo entrepreneurs can create promotional videos from a photo and voiceover. No equipment, no crew, no expensive production.
Companies can gather customer testimonial audio and animate it with a customer photo. The result is more engaging than reading text, but faster and cheaper than filming testimonials.
TikTok, Instagram Reels, and YouTube Shorts creators can quickly generate talking avatar videos for content series. Fast turnaround lets creators post frequently without constant filming.
VEED Fabric 1.0 is ideal for fast turnaround explainer videos. When you need to document a process or explain a feature and need results quickly, the speed of VEED Fabric 1.0 makes iteration practical. One minute is enough for a clear, direct explanation.
SaaS companies and service providers can create quick explainer videos for FAQs, feature highlights, or product updates. When you ship a new feature, generate a quick 30-second demo with VEED Fabric 1.0 instead of waiting for a full production video.
For richer performance, Kling Avatar 2 Pro, Kling Avatar 2, and OmniHuman 1.5 add hand stability, emotion, and camera movement on up to 60 seconds of audio. VEED Fabric 1.0 takes up to 5 minutes and specializes in speed and simplicity, making it ideal for quick-turnaround use cases.
Instructors and course creators can generate avatar-based lesson intros or announcements without filming. One photo per instructor, unlimited variations of audio and content.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the VEED Fabric 1.0 prompts for you. Every Craze plan, including Free, runs VEED Fabric 1.0 and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.085 per second of audio, with top-ups when you need more.
Quick marketing videos: Marketers and social media managers need talking videos fast. Small business and solo creators: Founders, freelancers, and solo entrepreneurs can create promotional videos from a photo and voiceover. Customer testimonials and case studies: Companies can gather customer testimonial audio and animate it with a customer photo. Social media content: TikTok, Instagram Reels, and YouTube Shorts creators can quickly generate talking avatar videos for content series.
VEED Fabric 1.0 is a talking avatar model that generates realistic speaking videos from a single photo and audio. It's designed as a fast and affordable alternative to traditional video production.
VEED Fabric 1.0 costs $0.085 per second of audio on Craze. Use the cost calculator on this page to estimate the cost for your video.
every Craze plan, including Free include VEED Fabric 1.0. Your plan provides monthly credits for avatar generation.
VEED announced Fabric 1.0 on September 15, 2025. The model was released as the world's first AI talking video model designed for speed and affordability.
VEED Fabric 1.0 takes up to 5 minutes of audio per generation on Craze, and the video runs as long as the audio.
Clear, well-lit headshots or shoulder shots work best. The model generates realistic lip sync and subtle facial expressions. Photos with good lighting and a visible face centered in the frame produce the strongest results.
Yes. Use voice recordings, text-to-speech, music, or any audio. The model will animate the avatar and generate lip sync to match the audio.
VEED Fabric 1.0 excels at fast, affordable talking videos, and it takes the longest audio of the avatar models on Craze. For richer emotional performance or hand gesture, OmniHuman 1.5 or Kling Avatar 2 Pro may be better suited.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video
