> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI Dance Replace v2 > Replace the person in a reference video with the character from your image. The original background, lighting, motion and audio track are kept — only the person is swapped. By default the whole reference video is used (it must be 5–30 seconds long). Pass `duration` to render only its first N seconds — billing follows that value. Optionally pass `prompt` to describe the output video (the character's appearance, the motion and the scene). **Tips** — a full-body image of a single character works best, and the reference video should show one clearly visible person. Everything else in the frame is kept as-is, including any logos, watermarks or text in the original video. **Pricing** — per second of generated video (rounded up), in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | per 5s | |---|---|---|---| | 480p | 2 | $0.04 | $0.20 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. ## OpenAPI ````yaml api-reference/video-generations/openapi-ai-dance-replace-v2.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - AI Dance Replace v2 description: Character replacement in a reference video. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: AI Dance Replace v2 description: >- Replace the person in a reference video with the character from your image. The original background, lighting, motion and audio track are kept — only the person is swapped. By default the whole reference video is used (it must be 5–30 seconds long). Pass `duration` to render only its first N seconds — billing follows that value. Optionally pass `prompt` to describe the output video (the character's appearance, the motion and the scene). **Tips** — a full-body image of a single character works best, and the reference video should show one clearly visible person. Everything else in the frame is kept as-is, including any logos, watermarks or text in the original video. **Pricing** — per second of generated video (rounded up), in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | per 5s | |---|---|---|---| | 480p | 2 | $0.04 | $0.20 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - ai_dance_replace_v2 description: Model name. Must be `ai_dance_replace_v2`. image_url: type: string format: uri description: >- Character image URL. This character replaces the person in the reference video. A full-body image of a single character works best. video_url: type: string format: uri description: >- Reference video URL, 5–30 seconds and at least 16 fps. The person in it is replaced; the background, motion and audio are kept. Videos longer than 30 seconds or shorter than 5 seconds are rejected. Use `duration` to render only the first N seconds of it. duration: type: integer minimum: 5 maximum: 30 description: >- Optional. Use only the first N seconds of the reference video. Defaults to the full video length. Must not exceed the actual video length — a longer value is rejected rather than silently clamped. Billing follows this value, so a shorter duration costs proportionally less. prompt: type: string maxLength: 2000 description: >- Optional. Describe the output video: the character's appearance (clothing, hair, style), the motion and the scene. Defaults to a neutral description. resolution: type: string enum: - 480p default: 480p description: >- Output resolution. Only 480p is supported; the aspect ratio follows the reference video. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - image_url - video_url example: model: ai_dance_replace_v2 image_url: >- https://cdn.goenhance.ai/user/goenhance/76115ad445ce26fbd5ad2c649a29e806.jpg video_url: >- https://cdn.goenhance.ai/user/upload-data/video-to-video/333768e610e442d02e8030693def0b6e.mp4 prompt: >- A young woman with short black hair wearing a red jacket and jeans, dancing in the same street scene responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 5.82 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 5.82 '2': summary: Invalid duration value: code: -1 msg: duration (30s) exceeds the reference video length (12s). '3': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.