Reference-guided video generation with text, image, video, and audio inputs.
The Seedance 2.0 API is ByteDance Seed's multimodal video generation API for cinematic short clips guided by text, image, video, and audio references. Preserve subject identity, composition, and motion while changing lighting, style, weather, camera feel, or specific scene elements.
Model capabilities
Use Seedance 2.0 from the same platform surface as the rest of your video and image stack: API keys, credits, logs, webhooks, and docs stay consistent across providers.
Use product shots, character images, first and last frames, or style references to control visual direction.
Attach short reference clips so the model can follow movement, composition, rhythm, and transition intent.
Provide music or sound references, or enable synchronized audio generation for richer short-form output.
Create short cinematic sequences with stronger scene flow, subject consistency, and production-ready pacing.
Send prompt, references, duration, aspect ratio, resolution, and callback URL to the video generation endpoint.
Use the returned task ID to poll status, or let the callback deliver completion and failure events.
Completed tasks return mirrored video URLs and metadata through the same response shape used by other models.
AI Video APIcurl -X POST https://api.aivideoapi.ai/v1/videos/generations \
-H "Authorization: Bearer sk-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedance-2.0",
"input": {
"prompt": "A cinematic product reveal with smooth camera motion",
"duration": 8,
"resolution": "1080p",
"ratio": "16:9"
}
}'Frequently asked questions
The Seedance 2.0 API is a multimodal video generation API by ByteDance Seed, exposed through AI Video API. It generates 4 to 15 second cinematic videos at 480p, 720p, or 1080p from text prompts plus optional image, video, and audio references, and returns hosted output URLs through callbacks or polling.
Sign in to AI Video API, open the dashboard, and create an API key. The same key works for Seedance 2.0, Seedance 2.0 Fast, and every other video and image model on the platform. Pay-as-you-go credits start working immediately after sign-up.
Seedance 2.0 is priced by output duration and resolution in credits per second: 18 cr/s at 480p, 38 cr/s at 720p, and 95 cr/s at 1080p. With a video reference attached, pricing drops to 12, 25, and 62 cr/s respectively. Seedance 2.0 Fast is 14.5 cr/s at 480p and 30.5 cr/s at 720p.
Seedance 2.0 supports text prompts, image references (first frame, last frame, product shots, character images, or style frames), short video references for motion and camera rhythm, and audio references for beat-matched generation. You can also enable native synchronized audio generation in the output clip.
A typical Seedance 2.0 task completes in 5 to 8 minutes. Generation is asynchronous: the API returns a task ID immediately, then delivers completion through a callback URL or status polling.
Seedance 2.0 (model id doubao-seedance-2.0) supports the full 480p to 1080p resolution range and is tuned for final production output. Seedance 2.0 Fast (doubao-seedance-2.0-fast) is optimized for 480p and 720p drafts and rapid batch testing at a lower per-second cost.
Yes. Set generate_audio to true in the request body and Seedance 2.0 will produce synchronized audio with the video. You can also pass a music or sound reference to bias rhythm and tone.
New AI Video API accounts receive a small starting credit balance that covers Seedance 2.0 draft generations at 480p. You can top up credits as you go — no monthly commitment or contract.
Pricing and usage
Standard draft generation
Lowest-cost reference workflow
Balanced production quality
Reference-guided 720p
Final cinematic output
Reference-guided 1080p
Create one API key, use one credit balance, and switch between video and image models without provider-specific plumbing.