Generate video

Create moving-image content from an input prompt or conditioning signal.

Desired outcome

Generated moving-image content, with synchronized audio where the selected model supports it.

Explore from the outcome

These documented connections are starting points for selection, not a ranked list.

Identifiable models documented for this function.

Gemini Omni Flash 1.1
Generate, edit, extend, and interpolate short videos from text, image, or video input.
Link evidence: Gemini Omni Flash model page
Kling Video 3.0
Generate and edit multi-shot video from prompts and visual references, with native audio.
Link evidence: Kling AI 3.0 launch, Kling AI quick start
Runway Gen-4.5
Generate video clips from text prompts or image-plus-text direction.
Link evidence: Runway available AI models, Creating with Gen-4.5
Seedance 2.5
Generate and extend up to 30-second audio-video clips from multimodal creative direction.
Link evidence: Introducing Seedance 2.5
Veo 3.1 Preview
Generate short videos with natively generated audio from text or image direction.
Link evidence: Veo 3.1 video generation guide
Wan2.1 T2V 1.3B
Generates short video from text prompts using a downloadable 1.3B checkpoint.
Link evidence: Wan2.1 T2V 1.3B model card
Wan2.2 T2V-A14B
Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
Link evidence: Wan2.2 T2V A14B model card

Last reviewed 2026-10-04