Annual Sale!Get 30% offClaim Now→
Enter a prompt or upload an image to generate a flagship-quality video with native audio.
Want faster video generation? Upgrade to Pro for priority processing and faster results.
Generated video with native audio will appear below
Result Time1-5 min
The most capable Seedance model to date, with sharper detail, stronger prompt following and steadier motion than Seedance 2.0.
Dialogue, sound effects and ambience are generated together with the video at no extra credit cost.
Text-to-video and image-to-video, 4-15 second duration, 480p or 720p, and six aspect ratios from 21:9 to 9:16.
Explore sample clips showcasing flagship video quality with native audio.

Original Image 1
Video Result 1
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
Seedance 2.5 is ByteDance's flagship Seedance video model. It generates video with native audio from text prompts or reference images, supporting up to 15 seconds at 480p or 720p.
Credits are charged per second of video: 54 credits per second at 480p and 112 credits per second at 720p. For example, a 5-second 720p clip costs 560 credits, while the same clip at 480p costs 270 credits.
Seedance 2.5 is the newer flagship, with higher visual fidelity, better prompt adherence and more consistent motion. Seedance 2.0, 2.0 Fast and 2.0 Mini remain available at lower credit costs when budget matters more than maximum quality.
Seedance 2.5 supports text-to-video and image-to-video. Upload a reference image as the first frame and combine it with a text prompt for more precise control over the result.
Yes. Audio is generated natively alongside the video by default, including dialogue, sound effects and ambience synchronized to the visuals. You can toggle audio off if you prefer silent output.
Seedance 2.5 supports 480p and 720p with six aspect ratios: 16:9, 4:3, 1:1, 3:4, 9:16 and 21:9. Duration is adjustable from 4 to 15 seconds.
Most videos finish in 1-5 minutes depending on duration, resolution and queue load. You can leave the page once generation starts — finished videos are always saved to My Videos.