Akool Video Face Swap

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

Parameter	Required	Description
source_image	Yes	Face images to swap onto the video (multiple allowed).
target_image	Yes	Face images to be replaced in the video (multiple allowed).
video	Yes	Video file to process (upload or public URL).
face_enhance	No	Enhance face quality after swapping (default: enabled).
enable_base64_output	No	Return base64 string instead of URL (API only).

How to Use

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

Face Mapping

The model matches source and target faces by order:

Source Image	Target Image	Result
Source 1	Target 1	Target 1's face replaced by Source 1
Source 2	Target 2	Target 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

Duration	Price
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.

Video Face Swap API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/akool/video-face-swap with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Video Face Swap below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/akool/video-face-swap" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4",
    "face_enhance": false,
    "enable_base64_output": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("akool/video-face-swap", {
        "video": "https://example.com/your-input.mp4",
        "face_enhance": false,
        "enable_base64_output": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "akool/video-face-swap",
    {
    "video": "https://example.com/your-input.mp4",
    "face_enhance": false,
    "enable_base64_output": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Video Face Swap API — Frequently asked questions

What is the Video Face Swap API?

Video Face Swap is a Akool model for AI inference, exposed as a REST API 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. You can call it programmatically or try it from the playground above.

How do I call the Video Face Swap API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/akool/akool-video-face-swap.

How much does Video Face Swap cost per run?

Video Face Swap starts at $0.050 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Video Face Swap accept?

Key inputs: `video`, `enable_base64_output`, `face_enhance`, `source_image`, `target_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/akool/akool-video-face-swap.

How long does Video Face Swap take to generate?

Average end-to-end generation time on WaveSpeedAI is around 382 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Video Face Swap outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Akool). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README