VideoGen Model 1
Text- and image-to-video model producing multi-shot videos up to 10 minutes with joint audio-video generation.
Overview
VideoGen Model 1 is the first video generation model from Y Combinator-backed VideoGen, Inc., announced October 20, 2026 with a limited private-partner rollout. It turns text prompts or up to 16 reference images into multi-shot videos up to ten minutes long, using a planning harness for screenplay, dialogue, shots and pacing, an automated pipeline that retries renders and joins clips, and joint audio-video attention to generate sound with picture. Outputs carry invisible watermarks. The company says it expects costs more than 50% below comparable models, but that figure is an internal estimate and official benchmarks and third-party validation are still in progress.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Text-to-video and image-to-video with up to 16 reference images
- Multi-shot output up to 10 minutes with user-set duration and aspect ratio
- Planning harness for screenplay, dialogue, shot list and pacing
- Character, object and location consistency across shots
- Joint audio-video attention for synchronized sound
- Invisible watermarks and guardrails against adult and illegal content
Use cases
- Long-form narrative and explainer video drafts
- Multi-shot ad and social video production
- Storyboard-to-video prototyping
Pricing
No final pricing published; company expects more than 50% below comparable models (internal estimate). $1 million in free credits for selected projects through end of 2026.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 20 Oct 2026
- Record updated
- 26 Oct 2026
- Record last checked
- 26 Oct 2026