Video Body Swap
Playground
Try it on WaveSpeedAI!Video Body Swap replaces the body in a target video with your face. Upload a face image and a body video to get a seamless swap. Ready-to-use REST inference API, no coldstarts, affordable pricing.
Features
Video Body Swap replaces the body in a target video with your face. Upload a face image and a body video — AI seamlessly composites your likeness onto the moving subject, frame by frame, with natural blending and consistent identity throughout the clip.
Why Choose This?
-
Seamless face-to-body compositing Advanced AI tracks the subject across every frame and blends your face naturally onto the body in motion, maintaining consistent identity and lighting.
-
Simple two-input workflow Just a face image and a body video — no masking, no manual keyframing, no technical setup required.
-
Wide range of use cases Works across talking head videos, dancing clips, fitness content, and more.
-
Production-ready API No cold starts, predictable per-second pricing, and a ready-to-use REST endpoint for seamless integration.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Face image to composite onto the body video. |
| video | Yes | Target body video. Billing is based on this video’s duration. |
How to Use
- Upload your face image — a clear, front-facing portrait with good lighting works best.
- Upload your body video — the video whose body you want to swap the face onto.
- Submit — AI processes the swap frame by frame and returns the finished video.
Pricing
$0.08 per second of input video, with a minimum charge of 5 seconds and a maximum billable duration of 120 seconds.
| Video Duration | Cost |
|---|---|
| 5s (minimum) | $0.40 |
| 10s | $0.80 |
| 30s | $2.40 |
| 60s | $4.80 |
| 120s (maximum) | $9.60 |
Billing Rules
- Minimum charge: 5 seconds
- Maximum billable duration: 120 seconds
- Videos longer than 120 seconds are capped at 120 seconds for billing purposes
Best Use Cases
- Creative content — Place yourself into dance, performance, or action videos.
- Marketing & advertising — Swap faces for personalized promotional video content.
- Entertainment & social media — Generate fun, shareable body-swap clips for Reels and TikTok.
- Developer integrations — Embed body swap functionality into apps and pipelines via the REST API.
Pro Tips
- Use a high-quality, well-lit face photo with a clear, unobstructed view for the most natural compositing result.
- Videos with a single clearly visible subject and stable lighting produce the cleanest swaps.
- Avoid heavily cropped or low-resolution face images — the more facial detail the AI has, the better the blend.
- For best results, the face in the image should be roughly front-facing and similar in angle to the subject in the video.
Notes
- Both image and video are required fields.
- Ensure URLs are publicly accessible if using links rather than direct uploads.
- Videos longer than 120 seconds are accepted but billing is capped at 120 seconds.
- Please ensure your content complies with WaveSpeed AI’s usage policies.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/video-body-swap" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | The URL of the face/head image. | |
| video | string | Yes | - | The URL of the target body video. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |