VideoGen Model 1
A single prompt. A finished, multi-shot video up to ten minutes long. Creative direction, audio, and video generation, together.
Limited private-partner rollout begins October 20, 2026.
Short films
Each film was generated from a single prompt, with no editing or post-production.
1 of 3
Built for the whole video.
Start with a prompt and optional image references. Model 1 plans the screenplay, dialogue, shots, and pacing, then generates and assembles video and audio while carrying context across scenes.
10 minutes
Generate finished, multi-shot videos up to ten minutes long.
Text + image
Begin with a prompt, with optional images to guide the visuals.
Video + audio
Dialogue, sound, and music, together.
More examples
Films, animation, and ads. Explore the model's raw outputs, with sound.
$1 million in free AI credits.
Early access and credits are primarily for filmmakers, creators, and studios making and sharing work. Students and amateurs are welcome. Some credits will also support journalists and software reviewers covering Model 1.
Apply from October 20: sign in, select Request access, and describe what you plan to create or cover. Allocations depend on your project scope and distribution plan. We plan to distribute credits through the end of 2026.
What to know.
For press and early demonstrations: press@videogen.io