faceswap
Swap Faces in Videos with AI
Swapping faces in videos manually is slow and requires specialized software. This skill automates the entire workflow using the verging.ai API, accepting local files or YouTube/Bilibili URLs as input and delivering the result directly.
Download the skill ZIP
Upload in Claude
Go to Settings → Capabilities → Skills → Upload skill
Toggle on and start using
Test it
Using "faceswap". Run /faceswap with video ./video.mp4 and face ./face.jpg
Expected outcome:
- Checking video duration: 22 seconds
- Credits needed: 22 (normal mode)
- Uploading video to cloud storage...
- Job created: job_id=295
- Progress: 25%... 50%... 75%... 100%
- Result: https://img.panpan8.com/face-swap/2026-05-31/result.mp4
Using "faceswap". Swap the face in a YouTube clip from 10-25 seconds in HD mode
Expected outcome:
- Downloading video from YouTube...
- Trimming to 10-25 seconds...
- Uploading trimmed video (15 seconds, HD = 45 credits)...
- Job created: job_id=296
- Status: COMPLETED after 45 seconds
- Result downloaded to: ./result_hd.mp4
Security Audit
Medium RiskThe skill is a documentation/instruction file (no executable code) that guides an AI assistant to run shell commands (yt-dlp, ffmpeg, curl) and make API calls to verging.ai. All 82 static findings are false positives in context: backtick patterns are markdown code examples, URLs are legitimate API endpoints, API key references are standard authentication documentation, and temp directory access is standard media processing. The combination of network + credentials + external commands is expected for this use case. No malicious intent detected. Risk level is medium due to the breadth of system access required.
Medium Risk Issues (1)
Low Risk Issues (4)
Risk Factors
⚙️ External commands (5)
🌐 Network access (5)
🔑 Env variables (3)
📁 Filesystem access (3)
Quality Score
What You Can Build
Content creator quick edits
Swap a face in a short clip for social media content without opening a video editor.
YouTube video face replacement
Provide a YouTube URL and a face image, and get the swapped result automatically downloaded.
Batch face-swap automation
Use the CLI command repeatedly with different inputs to process multiple videos in sequence.
Try These Prompts
Run /faceswap with video ./video.mp4 and face image ./face.jpg to swap the face.
Run /faceswap with video https://youtube.com/watch?v=xxx, face https://example.com/face.jpg, trimming from 10 to 25 seconds in HD mode and auto-downloading the result.
Run /faceswap with video ./input.mp4, a remote face image URL, and save the output to /tmp/result.mp4.
First check my verging.ai credit balance, then run /faceswap with the provided video and face URL, trim to 15 seconds, use HD mode, and download the result.
Best Practices
- Set the VERGING_API_KEY environment variable before running the skill to avoid passing the key in commands
- Trim videos to the shortest needed segment to minimize credit consumption
- Use normal mode for previews and HD mode only for final output to save credits
- Clean up /tmp/verging-faceswap/ after processing to avoid leaving media files on disk
Avoid
- Do not pass the API key directly in the command line where it may appear in shell history or process listings
- Do not use JSON body (-d) for the upload-video endpoint; it requires multipart form data (-F)
- Do not attempt to upload the face image separately via /upload-video; the create-job endpoint accepts it directly as swap_image=@path