skills.rest
X-manist
X-manistCOMMUNITY
Explore all skills by this author →
GitHub

faceswap

Swap faces in videos using the HeyGen workflows API.

Updated Jul 16, 2026
Search Tags:#api#face swap#video generation#ai video#heygen#avatar video#personalized video
One-click install
npx skills add https://github.com/X-manist/Cohmira --skill faceswap-x-manist
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faceswap
Source: https://github.com/X-manist/Cohmira/tree/main/src/builtin-plugins/openmontage/.agents/skills/faceswap
Command: npx skills add https://github.com/X-manist/Cohmira --skill faceswap-x-manist

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Replacing a face in a video normally requires specialized editing software and manual frame-by-frame work. This Skill automates face swapping by calling the HeyGen API, turning it into a simple submit-and-poll workflow. ## Core Features & Use Cases - AI Face Swap Execution: Submit a source face image and a target video to HeyGen's FaceswapNode workflow and receive a processed video URL. - Async Job Management: Poll workflow execution status every 10 seconds until completion, with handling for failed and not_found states. - Workflow Chaining: Combine with HeyGen avatar video generation to produce personalized videos with a custom face. - Use Case: A marketing team generates an avatar spokesperson video, then swaps in the CEO's face from a headshot photo to create a personalized announcement clip. ## Quick Start Swap the face from my headshot photo into this video using the HeyGen API and give me the resulting video URL.

Frequently Asked Questions about faceswap

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I swap a face in a video with the HeyGen API?▼

POST to https://api.heygen.com/v1/workflows/executions with workflow_type set to FaceswapNode, plus input.source_image_url and input.target_video_url. Then poll GET /v1/workflows/executions/{execution_id} until the status is completed and read the output video_url.

How long does HeyGen face swap processing take?▼

Face swap is GPU-intensive and typically takes 1-3 minutes. Poll the execution status endpoint every 10 seconds, and allow a generous timeout such as 10 minutes for longer videos.

What kind of source image works best for face swapping?▼

Use a clear, front-facing photo containing exactly one face with good lighting. Higher resolution face photos produce better swap results, and images with multiple faces should be avoided.

Can I chain face swap with HeyGen avatar video generation?▼

Yes. First run an AvatarInferenceNode workflow to generate an avatar video, wait for it to complete, then pass its output video URL as the target_video_url to a FaceswapNode execution with your custom face image.

Why does my HeyGen face swap execution fail or return not_found?▼

A failed status usually indicates invalid or inaccessible source image or target video URLs, while not_found means the execution_id is wrong or expired. Verify both URLs are publicly reachable and the X-Api-Key header is valid.

Related Skills

Explore More Content & Communication Skills→
video-production-buddyvideo-production-buddy
602

faceswap

Automate face swapping in videos via HeyGen's FaceswapNode API.

Official
Intermediate
refly-airefly-ai
199

video-creator

Generates short AI-powered videos and scripts for social media platforms.

Official
Intermediate
xingBaGanxingBaGan

heygen

Generate videos and avatars from text and images using your own API credentials.

Community
Advanced
RepairYourTechRepairYourTech
6

ollama

Run open-source LLMs locally via the Ollama runtime REST API.

Community
Intermediate