Akool Video Face Swap

Akool Video Face Swap

Playground

Try it on WaveSpeedAI!

AKOOL Video Face Swap replaces faces in videos from a single image, supporting multiple faces for seamless, realistic swaps. Price starts at $0.05 per video second with a minimum charge of 10 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Akool Video Face Swap is a powerful AI-powered face swapping model that replaces faces in videos with new ones. Upload source faces and their corresponding target faces, provide a video, and the model seamlessly swaps each face — perfect for content creation, entertainment, and creative projects.


Why It Stands Out

  • Multi-face swapping: Swap multiple faces in a single video simultaneously.
  • Face-to-face mapping: Match each source face to its corresponding target face.
  • Face enhancement: Optional post-swap face quality enhancement for better results.
  • High-quality output: Produces realistic, seamless face replacements.
  • Long video support: Process videos up to 10 minutes (600 seconds).

Parameters

ParameterRequiredDescription
source_imageYesFace images to swap onto the video (multiple allowed).
target_imageYesFace images to be replaced in the video (multiple allowed).
videoYesVideo file to process (upload or public URL).
face_enhanceNoEnhance face quality after swapping (default: enabled).
enable_base64_outputNoReturn base64 string instead of URL (API only).

How to Use

  1. Upload source images — add face images that will appear in the final video.
  2. Upload target images — add face images to be replaced (match order with source images).
  3. Upload your video — provide the video containing faces to swap.
  4. Enable face enhancement (recommended) — improves face quality after swapping.
  5. Click Run and wait for processing.
  6. Preview and download the result.

Face Mapping

The model matches source and target faces by order:

Source ImageTarget ImageResult
Source 1Target 1Target 1’s face replaced by Source 1
Source 2Target 2Target 2’s face replaced by Source 2

Add multiple source/target pairs to swap multiple faces in the same video.


Best Use Cases

  • Content Creation — Create engaging face-swap videos for social media.
  • Entertainment — Produce fun videos with friends and family.
  • Film & Production — Replace faces for creative or practical purposes.
  • Marketing — Create personalized video content at scale.
  • Dubbing & Localization — Swap faces for regional content adaptation.

Pricing

DurationPrice
10 seconds$0.50
30 seconds$1.50
60 seconds$3.00

Billing Rules

  • Billed per second at $0.05
  • Minimum charge: 10 seconds
  • Maximum duration: 600 seconds (10 minutes)

Pro Tips for Best Quality

  • Use high-resolution, front-facing source images with clear facial features.
  • Ensure target images match the faces appearing in the video.
  • Keep face enhancement enabled for smoother, higher-quality results.
  • Videos with well-lit, forward-facing subjects produce the best swaps.
  • Match the number of source and target images correctly.

Notes

  • Ensure uploaded image and video URLs are publicly accessible.
  • Processing time varies based on video length and current queue load.
  • Please ensure your content complies with usage guidelines and respect individuals’ likeness rights.

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'
{
  "source_image": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "target_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",
  "face_enhance": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/akool/video-face-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
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
source_imagearray<string>Yes-1 ~ 5 itemsSource face image URL to be swapped into the video
target_imagearray<string>Yes-1 ~ 5 itemsTarget face image URL that will be replaced in the video
videostringYes-Input video URL for face swapping
face_enhancebooleanNofalse-Whether to enhance face quality after swapping
enable_base64_outputbooleanNofalse-If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<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.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.