Image to Video (Result)
16:9An octopus on the sandy seafloor wrapping its arms around a soccer ball, clear blue water, realistic underwater physics
Seedance 2.0
ID:
bytedance/seedance-2Seedance 2.0 video generation API by ByteDance — up to 1080p with native audio and dialogue, image-to-video, and clips from 4 to 15 seconds.
Text to videoImage to videoAudio generation1080p
Input
OutputView all
Output will appear here
Pricing
480p
$0.12/s
720p
$0.27/s
1080p
$0.66/s
Examples
Image to Video (Source)
16:9An octopus resting beside a soccer ball on the ocean floor, sunlight filtering through the water
Overview
Seedance 2.0 is ByteDance's second-generation video model, released in February 2026. It generates video with native audio — dialogue, sound effects, and ambient noise are produced alongside the visuals in a single pass, removing the need for separate audio post-production. The model powers AI video features in CapCut and Dreamina.
Use cases
Product reveals and unboxing animations for e-commerce. Social media reels and short-form content with matching soundtracks. Image-to-video conversion — upload a still and animate it with motion and optional audio. Narrative clips with spoken dialogue for advertising or explainer content.
Inputs
All parameters are passed in the input object of the run request.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description (3–20000 chars) |
| aspect_ratio | No | Default 16:9. Options: 1:1, 3:4, 4:3, 9:16, 16:9, 21:9 |
| resolution | No | Default 720p. Options: 480p, 720p, 1080p |
| duration | No | Video length in seconds (4–15). Default 5 |
| generate_audio | No | Generate audio track. Default false |
| image_urls | No | First frame image (max 1, max 10 MB) for image-to-video |
Prompt tips
Describe camera movement and scene pacing
Seedance 2.0 responds well to cinematic direction. Phrases like "slow dolly forward," "overhead tracking shot," or "quick cut to close-up" improve coherence.
Keep audio prompts visual
When generate_audio is enabled, the model infers audio from the scene description. Write prompts that imply sound — "rain hitting a window," "footsteps on gravel" — rather than describing the audio directly.
Use the full duration range strategically
Short clips (4–5s) work best for single-action shots. For sequences with camera transitions or narrative beats, push toward 10–15 seconds.
Limitations
- Maximum 15 seconds per generation
- Audio generation increases credits cost
- Prompt minimum is 3 characters
- Only one first-frame image allowed for image-to-video (max 10 MB)
- 1080p significantly increases generation time and cost compared to 720p
FAQ
Does Seedance 2.0 generate audio?
Yes. Set generate_audio to true and the model produces synchronized dialogue, sound effects, and ambient audio in one pass. This adds to the per-run cost.
What's the maximum video length?
15 seconds. You can set any integer from 4 to 15 via the duration parameter. The default is 5 seconds.
Can I animate a still image?
Yes. Upload a first-frame image via image_urls and the model generates video starting from that frame.