Explore concepts with text to video
Turn a scene description into a moving concept for pitches, previsualization, and creative exploration.
Built for these real workflows
Animate still images
Bring characters, products, and keyframes to life with controlled movement, camera motion, and duration.
Create consistent shots from references
Use first and last frames or multiple references to build coherent shots for storyboards, short dramas, and social content.
Four generation modes for different starting materials
- •Text to video with no reference file.
- •Image to video from one key visual.
- •First and last frame control with one or two images.
- •Omni reference mode with up to fifteen image or video inputs.
Shot controls from the Recapo free canvas
Choose Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Kling 3.0, or Kling 3.0 Omni, then configure aspect ratio, 480p to 1080p resolution where supported, a model-dependent 3–30 second duration, audio policy, and one to four outputs.
Frequently asked questions
Which video generation modes are supported?
Text-to-video, image-to-video, first/last frame, and omni reference modes are supported.
Can a generation include audio?
Audio behavior follows the selected model and reference type. Seedance uses synchronized audio; Kling allows an audio toggle without a video reference and disables it when a video reference is present.
When are credits deducted and refunded?
Credits are deducted immediately when each task is accepted. Only final failures caused by the platform are refunded automatically.