> ## Documentation Index > Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create video > Seedance (2.0 / 2.5) async video create. **Path:** `POST https://api.omniall.ai/v1/video/generations` Also accepts `POST /v1/videos`. Poll with returned `id` / `task_id`. Model ids from the [Model Square](https://omniall.ai/pricing) and [Seedance status](https://omniall.ai/seedance-status). Examples: `db-sd2.0-1080p`, `db-sd2.5-1080p`, `doubao-seedance-2-0-260128-1080p`, etc. Auth: `Authorization: Bearer sk-...` ## OpenAPI ````yaml openapi/seedance-video.yaml POST /v1/video/generations openapi: 3.1.0 info: title: Omniall AI — Seedance version: 1.0.0 description: >- Seedance (2.0 / 2.5) async video create. **Path:** `POST https://api.omniall.ai/v1/video/generations` Also accepts `POST /v1/videos`. Poll with returned `id` / `task_id`. Model ids from the [Model Square](https://omniall.ai/pricing) and [Seedance status](https://omniall.ai/seedance-status). Examples: `db-sd2.0-1080p`, `db-sd2.5-1080p`, `doubao-seedance-2-0-260128-1080p`, etc. Auth: `Authorization: Bearer sk-...` servers: - url: https://api.omniall.ai security: [] paths: /v1/video/generations: post: tags: - Seedance summary: Create video description: >- Seedance (2.0 / 2.5) async video create. **Path:** `POST https://api.omniall.ai/v1/video/generations` Also accepts `POST /v1/videos`. Poll with returned `id` / `task_id`. Model ids from the [Model Square](https://omniall.ai/pricing) and [Seedance status](https://omniall.ai/seedance-status). Examples: `db-sd2.0-1080p`, `db-sd2.5-1080p`, `doubao-seedance-2-0-260128-1080p`, etc. Auth: `Authorization: Bearer sk-...` operationId: seedanceCreateVideo parameters: - name: Authorization in: header required: true schema: type: string example: Bearer sk-... description: Bearer API key, e.g. `Bearer sk-...`. requestBody: required: true content: application/json: schema: type: object required: - model - prompt description: Seedance async create body (`POST /v1/video/generations`). properties: model: type: string description: >- Video model id. Model ids from the [Model Square](https://omniall.ai/pricing) and [Seedance status](https://omniall.ai/seedance-status). Examples: `db-sd2.0-1080p`, `db-sd2.5-1080p`, `doubao-seedance-2-0-260128-1080p`, etc. example: db-sd2.5-1080p prompt: type: string description: >- Text prompt. Subject, scene, camera motion, style. Or use `content` text part. example: >- City night scene, slow push along a wet street, neon reflections duration: type: integer description: >- Duration in seconds (often 4–15). Use `-1` to follow reference video length for edit tasks. Alias: `seconds`. example: 5 seconds: type: string description: Duration as string; equivalent to `duration`. example: '5' ratio: type: string description: 'Aspect ratio. Aliases: `size`, `aspect_ratio`.' enum: - '21:9' - '16:9' - '4:3' - '1:1' - '3:4' - '9:16' example: '16:9' size: type: string description: Alias of `ratio`. aspect_ratio: type: string description: Alias of `ratio`. images: type: array items: type: string description: >- Reference image URLs. Ignored when first/last frames are set. image: type: string description: Single reference image URL. first_frame: description: >- First frame URL (string or array). Aliases: `start_frame`, `first_frame_url`. oneOf: - type: string - type: array items: type: string last_frame: description: >- Last frame URL (string or array). Aliases: `end_frame`, `last_frame_url`. oneOf: - type: string - type: array items: type: string start_frame: description: Alias of `first_frame`. oneOf: - type: string - type: array items: type: string end_frame: description: Alias of `last_frame`. oneOf: - type: string - type: array items: type: string reference_images: type: array items: type: string description: Reference image URLs. reference_videos: type: array items: type: string description: Reference video URLs. reference_audios: type: array items: type: string description: Reference audio URLs. generate_audio: type: boolean description: >- Whether to generate audio track. Also `extra_body.generate_audio`. example: true extra_body: type: object additionalProperties: true description: Extensions, e.g. `generate_audio`. omni_reference_task_type: type: string description: >- Omni-reference task type (e.g. `edit`). Often with `duration: -1`. example: edit content: type: array description: >- Multimodal content parts (alternative to top-level reference_* fields). items: type: object properties: type: type: string enum: - text - image_url - video_url - audio_url text: type: string url: type: string role: type: string image_url: type: object additionalProperties: true video_url: type: object additionalProperties: true audio_url: type: object additionalProperties: true examples: text_to_video: summary: Text-to-video value: model: db-sd2.5-1080p prompt: >- City night scene, slow push along a wet street, neon reflections, cinematic DOF duration: 5 ratio: '16:9' generate_audio: true multi_image_reference: summary: Multi-image reference value: model: db-sd2.0-1080p prompt: >- Keep the character look from these images; generate a turn-and-walk shot duration: 5 ratio: '16:9' images: - https://example.com/character-front.jpg - https://example.com/character-side.jpg generate_audio: true omni_multimodal: summary: Omni multimodal reference value: model: db-sd2.5-1080p prompt: >- Keep product look; follow camera motion from video; sync rhythm to audio duration: 10 ratio: '16:9' reference_images: - https://example.com/product.png reference_videos: - https://example.com/motion-guide.mp4 reference_audios: - https://example.com/music-guide.mp3 generate_audio: true first_last_frame: summary: First & last frame value: model: db-sd2.0-720p prompt: >- From morning to dusk, clouds drift, light transitions naturally duration: 5 ratio: '16:9' first_frame: https://example.com/morning.png last_frame: https://example.com/dusk.png first_last_frame_v2: summary: First & last frame · alt arrays value: model: db-sd2.0-720p prompt: From morning to dusk, clouds drift duration: 5 ratio: '16:9' start_frame: - https://example.com/morning.png end_frame: - https://example.com/dusk.png first_last_frame_v3: summary: First & last frame · content roles value: model: db-sd2.5-720p prompt: Clouds drift, light transitions duration: 5 ratio: '16:9' content: - type: image_url url: https://example.com/morning.png role: first_frame - type: image_url url: https://example.com/dusk.png role: last_frame content_multimodal: summary: content multimodal form value: model: doubao-seedance-2-0-260128-720p content: - type: text text: Keep product appearance consistent - type: image_url url: https://example.com/product.png role: reference_image - type: video_url url: https://example.com/motion-guide.mp4 role: reference_video - type: audio_url url: https://example.com/music-guide.mp3 role: reference_audio duration: 10 aspect_ratio: '16:9' extra_body: generate_audio: true responses: '200': description: Task accepted. Poll with `id` or `task_id`. content: application/json: schema: type: object properties: id: type: string description: Task id for polling. task_id: type: string description: Same as `id`. object: type: string status: type: string description: Task status. progress: description: Progress percent or numeric. created_at: type: integer example: id: task_MVPe8uCjxrxe8szgdZWJvRub0ccg8gi0 task_id: task_MVPe8uCjxrxe8szgdZWJvRub0ccg8gi0 status: submitted created_at: 1710000000 '400': description: Invalid request '401': description: Unauthorized '429': description: Rate limited ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.