← All models
US-hosted ByteDance Seedance 2.5 generates video with native audio from up to 30 images, 10 videos, and 10 audio references. Supports reference-guided generation, video editing, and extension at 480p or 720p.
Example
Details
- Accepts
- text + audio + image + video
Pricing
- Input
- 2675 cr / 1M tokens
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. Note that results may still vary slightly even with the same seed. |
| task | stringenum: auto, reference, editing, extension | The type of video generation task. Reference uses the supplied media as guidance. Editing modifies a reference video and automatically coerces aspect_ratio and duration to auto. Extension continues a reference video and automatically coerces aspect_ratio to auto. Auto leaves the task type unset so t… |
| codec | stringenum: auto, H264, H265 | 'auto' retains default video codec behaviour; 'H264' uses H.264; 'H265' uses H.265. |
| draft | boolean | Generate a draft preview at 480p, overriding resolution. Returns a draft_id for completing the draft at 1080p within 7 days. |
| prompt | — | The text prompt used to generate the video. |
| duration | stringenum: auto, 4, 5, 6, 7, 8… | Duration of the video in seconds. Supports 4 to 30 seconds, or auto to let the model decide based on the prompt. |
| audio_urls | array | Reference audio to guide video generation. Refer to them in the prompt as @Audio1, @Audio2, etc. Supported formats: MP3, WAV. Up to 10 files. Each file must be 1.8 to 30.2 seconds and no larger than 15 MB; combined duration must not exceed 30.2 seconds. |
| image_urls | array | Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF. Max 30 MB per image. Up to 30 images. Total files across all modalities must not exceed 50. |
| resolution | stringenum: 480p, 720p, 1080p | Video resolution - 480p for faster generation, 720p for balance, 1080p for high quality. |
| video_urls | array | Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 10 videos. Each video must be 1.8 to 30.2 seconds and no larger than 200 MB; combined duration must not exceed 30.2 seconds. Dimensions must be 300 to 6,000 pixels per… |
| end_user_id | — | The unique user ID of the end user. |
| aspect_ratio | stringenum: auto, 21:9, 16:9, 4:3, 1:1, 3:4… | The aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide. |
| bitrate_mode | stringenum: standard, high | Output bitrate mode. 'high' requests a higher-quality, larger-file encode from the model; 'standard' uses the default bitrate. |
| generate_audio | boolean | Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| video | — | The generated video file. |
| draft_id | — | The draft ID, or null when draft mode is disabled. Complete this draft within 14 days (7 days for US drafts) using the same account. |