ByteDance's Seedance 2.5 Flash text-to-video endpoint turns a written shot description into a 4–30 second clip at 480p or 720p, with speech, effects and ambience generated in the same pass. Choose one of six frame shapes or adaptive, and ask for the final frame as a JPEG to start the next shot.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
after-hours-slow-dance Five seconds at 720p, 16:9, audio on: 1280×720 at 24 fps, 5.056 seconds long. The couple sway forehead to forehead by the rainy window with the chairs stacked on the tables, her hand resting on his shirt, and the line written in quotes, "Stay for one more song.", is clearly spoken in the generated track. The task finished about two minutes after submission.
- 720p
- 16:9
- audio
- Output4s
raincoat-crosswalk-sprint Four seconds at 480p, 16:9, audio on: 854×480 at 24 fps, 4.064 seconds long, with an AAC stereo track. The clip showed her running across, ducking under the awning and laughing, as written; the same request with return_last_frame on also returned an 854×480 JPEG of the final frame.
- 480p
- 16:9
- audio
This example starts at $0.115 per output second. The Playground updates the estimate when you change the settings.
