Why choose it
- Sound with every clip
- Up to 2K
- Up to 9 reference images
- Repeatable takes with a seed
Original model creator
HeyGen
Run HeyGen Video in your browser: 5–15 second clips with generated sound at 480p, 768p, 1080p, or 2K from text, a still, or up to 9 references.
Runs online, no installIncluded in plans from $19/moSpecs checked 4 October 2026

Official sample · Results vary by prompt and settings
Inspect the sample frame.
Story
Turn a written story into a narrated multi-shot film. HeyGen Video is the shot language on this page — start a story after signup, then come back here when you want a single directed take.
Example output
Story arc
Direct answer
HeyGen Video is the low-cost catalog choice for clips with sound. Generate 5–15 seconds at 480p, 768p, 1080p, or 2K from text, a starting image, or up to 9 reference images, with a seed and optional prompt enhancement.
Best for
Low-cost clips with generated sound from a prompt, one still, or a set of reference images.
Technical readout
Catalog modes: Text prompt · Animate image · References. Advanced controls: Seed, Prompt enhancement. References: Up to 9.
Catalog delta
Differences below are from the live Video Lab catalog—duration, resolution, audio, modes, and controls—not from a ranked shoot-out.
How it compares
Side-by-side from the Video Lab catalog. Try both with the same prompt when the modes overlap.
Spec
HeyGen Video
MiniMax H3
Duration
HeyGen Video
5–15 seconds
MiniMax H3
5–15 seconds
Resolution
HeyGen Video
480p, 768p, 1080p, 2K
MiniMax H3
480p, 768p, 2K, 4K
Aspect ratios
HeyGen Video
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
MiniMax H3
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Audio
HeyGen Video
Native audio
MiniMax H3
Native audio
Modes
HeyGen Video
Text prompt, Animate image, References
MiniMax H3
Text prompt, Animate image, First → last, References
References
HeyGen Video
Up to 9
MiniMax H3
Up to 9
Advanced controls
HeyGen Video
Seed, Prompt enhancement
MiniMax H3
Seed, Prompt enhancement
Prompt direction
Describe who is on screen, what they do, and the sound the scene should carry.
Prompts that work
Questions, answered
HeyGen Video is best for low-cost clips with generated sound, from a prompt, a single still, or a set of reference images.
Yes. Open HeyGen Video in Clip Studio Video Lab to generate in the browser. Generate 5–15 second shots at 480p, 768p, 1080p, or 2K from text, a start image, or up to 9 references. Sign in to generate; this model page is public.
HeyGen Video is built on MiniMax H3 and post-trained by HeyGen. Both generate 5–15 second clips with sound.
No. Video Lab supports a starting image or a reference pack of up to 9 images on HeyGen Video.
HeyGen Video uses your monthly generation allowance. Video Lab is included in every Clip Studio plan, from $19/mo. Each plan includes a monthly generation allowance. Model, duration, resolution, and audio decide how much of it a clip uses, and each setup is quoted before you generate. Plan details live on the pricing page.
Change the lens
Official sample
Official sample
Official sample
Official sampleHeyGen lens selected
Paste a story or script. Clip Studio plans cinematic shots, narrates them, and renders a film you can download.