Video Head Swap API documentation

Replace one or more complete heads in a target video while preserving its motion, body, scene, text, head pose, gaze, expression, and mouth movement. Reference images control identity, hairstyle, and skin tone; an optional prompt selects and maps people. Target videos must be 5–15 seconds.

Endpoints

Contract item	Value
Capability	`video-head-swap`
Submit	`POST https://vidmage.ai/api/v1/video-head-swap/submit`
Query	`POST https://vidmage.ai/api/v1/video-head-swap/query`
Task identifier	`taskId`
Result field	`videoUrl`

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Product guide: AI Head Swap API for Photos and Videos

Parameters and input rules

Field	Type	Required	Default	Meaning and limits
`targetVideoUrl`	`string`	Yes	Not specified	Target-video fileUrl returned by upload_files.
`referenceImageUrls`	`string[]`	Yes	Not specified	One to 4 publicly reachable head-reference image URLs, ordered to match the requested people. Minimum items: `1` Maximum items: `4`
`customPrompt`	`string`	No	Not specified	Optional targeting instructions that identify which person or people to replace and map them to Reference 1 through Reference 4. Maximum characters: `1000`

Measured media limits

Input	Rule
`targetVideoUrl`	The server measures this media for billing. Maximum 15 seconds. Do not send `duration` in the submission body.

Example request

{
  "targetVideoUrl": "https://vidmage.ai/assets/models/hailuo-ai-video-generator/skincare-ad.mp4",
  "referenceImageUrls": [
    "https://vidmage.ai/assets/images/samples/smiling-man-sweater.webp"
  ]
}

# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/video-head-swap/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"targetVideoUrl":"https://vidmage.ai/assets/models/hailuo-ai-video-generator/skincare-ad.mp4","referenceImageUrls":["https://vidmage.ai/assets/images/samples/smiling-man-sweater.webp"]}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the completed head-swapped video. Read videoUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/video-head-swap/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "videoUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Credits

Component / option	Rate	Minimum
Video duration	15 credits / second	75 credits

The example uses the duration shown above. The server measures uploaded media for billing; this duration is only supplied to the estimate.

Duration is rounded up to whole seconds before applying the minimum duration and per-second rate.

Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.

Integration guides

Authentication · File uploads · Task lifecycle · Error recovery · MCP