All models
video generation
HeyGen Video 1.0
HeyGen Video 1.0 is HeyGen’s general video generation model, with native audio on every clip. Gobostock exposes text-to-video, a start frame, and up to nine reference images that the prompt can name as <Picture 1>, <Picture 2>, and so on, at 480p or 768p in six aspect ratios from 21:9 to 9:16, with clips of 5 to 15 seconds and an optional prompt enhancer.
From 58 Gobostock credits; surcharges or usage-based pricing may apply where shown in the tool quote. The quote shown in the tool is the one you pay.
No sample published yet.
Best for
- Short character and product clips that must keep a referenced look
- Vertical social clips with sound at a low cost per second
Known limits
- It tops out at 768p.
- A start frame cannot be combined with reference images in the same request.
- Audio is always generated, so silent output requires post-processing.
Capabilities
- Text-to-video and image-to-video with always-on native audio
- Up to nine reference images for characters, products, and style
- 480p and 768p output in six aspect ratios, 5 to 15 seconds
Inputs
- Text prompt
- Duration and output format
- Optional supported image, video, or audio references
Outputs
- MP4 video
Compare