ホーム
アセット
マイ作品
Models
ボイスライブラリ
開発者
ブログ
日本語
料金
ログイン
Models/Video/Seedance 2.0 Pro

ByteDance: Seedance 2.0 Pro

  • Text to video
  • Image to video
  • First/last frame
  • Reference video
  • Native audio
API referenceUse in AI動画生成

Seedance's quality tier, and the widest input surface in the video line: text, image and first/last frame, plus a reference video to drive camera work and pacing, with native audio on the way out.

Pro and Fast are two tiers of the same model and differ only in resolution — Pro reaches 1080p, Fast does not. Finish on Pro, test shots on Fast.

Strengths

  • Takes all four inputs: text, image, first/last frame, reference video
  • The only video model with both reference video and native audio
  • 480p / 720p / 1080p, 4 to 15 seconds, six ratios including 21:9

Limitations

  • No 4:5 or 5:4
  • Reference video input has to be 2 to 15 seconds
  • Rate limited to 5 RPM

Capabilities

CapabilityValue
Text to videoYes
Image to videoYes
First/last frameYes
Reference videoYes
Native audioYes
Lip sync–No
Motion transfer–No

Specs and limits

ParameterValue
Aspect ratio16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9

How it is billed

按分辨率 × 时长，生成前实时估价

Standard pricesCredits
720p · 5 秒94
1080p · 5 秒233

Figures come from the same estimator the generation form calls before you spend anything.

Alternatives

  • Seedance 2.0 FastDrafts and batches of test shots — the low-latency lane of the same model, minus 1080p.
  • Wan 3.0 PrimeAnything longer than 15 seconds. Wan 3.0 reaches 30; Seedance stops at 15.

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/video-generation/generate" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "doubao-seedance-2-pro","content": [{"type": "text","text": "A cinematic aerial shot of a quiet coastal city at sunrise"}]}'
  • API reference
  • SDK & CLI
  • Agent Skills

Similar models

  • Seedance 2.0 Fast
  • PPixVerse
  • Wan 3.0
  • Wan 3.0 Prime
  • MiniMax H3