{
  "markdown": "# verging.ai Agent Skills\n\nAI-powered media processing and AI service skills for AI coding agents.\n\n## Demo\n\n### Face Swap\n[![Face Swap Demo](https://img.youtube.com/vi/xvlZe4uqvY4/maxresdefault.jpg)](https://youtu.be/xvlZe4uqvY4)\n▶️ Click to watch demo video\n\n### Video Enhancement\n![Video Enhancement Demo](https://raw.githubusercontent.com/revisual-ai/video-enhancer-demo/master/demo/before_after.gif)\n\n## Features\n\n### Face Swap\nAI-powered face swap service - Use verging.ai directly from command line.\n\n- Support local video files and images\n- Support remote video URLs (YouTube, Bilibili, etc.)\n- Support remote image URLs\n- Auto-download remote resources\n- Real-time progress tracking\n- Video trimming (specify start/end time)\n\n### Background Removal (background-remover)\nAI one-click background removal to generate transparent PNG images.\n\n- **Perfect for**: E-commerce product photos, portrait background removal, design materials\n- Support local images (JPG, PNG, WebP)\n- Support remote image URLs\n- Auto-download remote resources\n- Real-time progress tracking\n- Maximum file size: 10MB\n\n### Video Enhancement (video-enhancement)\nAI video enhancement to upscale resolution, denoise, and sharpen videos.\n\n- **Perfect for**: Old video restoration, content creation, surveillance footage improvement\n- Support 2x and 4x upscale\n- Support local video files (MP4, MOV, AVI, MKV, WebM)\n- Support remote video URLs (YouTube, Bilibili, etc.)\n- Auto-download remote resources\n- Real-time progress tracking\n- Video trimming (specify start/end time)\n- Maximum video duration: 30 seconds\n\n### Chat (chat)\nAI chat completion proxy - Access GPT-4o and other LLMs.\n\n- Support streaming and non-streaming modes\n- Multi-turn conversation\n- Token-based post-deduct billing\n\n### Text-to-Speech (tts)\nAI text-to-speech - Convert text to natural speech audio.\n\n- 6 voices: alloy, echo, fable, onyx, nova, shimmer\n- Adjustable speed (0.25x - 4.0x)\n- Multiple formats: mp3, opus, aac, flac\n- Maximum text: 4096 characters\n\n### Speech-to-Text (stt)\nAI speech-to-text - Transcribe audio files to text.\n\n- Supports mp3, mp4, wav, webm, m4a and more\n- Auto language detection\n- Maximum file size: 25 MB\n\n### Image Generation (imagegen)\nAI image generation - Generate images from text prompts.\n\n- Models: gpt-image-1, dall-e-3\n- Multiple sizes and quality levels\n- Batch generation up to 4 images\n\n### Vision Analysis (vision)\nAI vision analysis - Analyze images and answer questions.\n\n- Supports image URL and local file upload\n- GPT-4o powered visual understanding\n- Maximum image size: 20 MB\n\n## Installation\n\n```bash\n# Install all skills\nnpx skills add verging-ai/agent-skills\n\n# Or install individually\nnpx skills add verging-ai/agent-skills --skill faceswap\nnpx skills add verging-ai/agent-skills --skill background-remover\nnpx skills add verging-ai/agent-skills --skill video-enhancement\nnpx skills add verging-ai/agent-skills --skill chat\nnpx skills add verging-ai/agent-skills --skill tts\nnpx skills add verging-ai/agent-skills --skill stt\nnpx skills add verging-ai/agent-skills --skill imagegen\nnpx skills add verging-ai/agent-skills --skill vision\n```\n\n## Usage\n\n### Face Swap\n\n```bash\n# Basic usage\n/faceswap --video ./input.mp4 --face ./my-face.jpg\n\n# Specify time range\n/faceswap -v ./video.mp4 -f ./face.jpg --start 5 --end 30\n\n# Use remote video\n/faceswap -v \"https://youtube.com/watch?v=xxx\" -f ./face.jpg --hd\n\n# Auto download result\n/faceswap -v ./video.mp4 -f ./face.jpg --download\n```\n\n### Face Swap Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --video | -v | Target video file or URL | Required |\n| --face | -f | Face image file or URL | Required |\n| --start | -s | Start time in seconds | 0 |\n| --end | -e | End time in seconds | Video duration |\n| --hd | -h | HD mode (3 credits/sec vs 1 credit/sec) | false |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n| --output | -o | Output directory | Current dir |\n| --download | -d | Auto download result | false |\n\n### Background Removal\n\n```bash\n# Basic usage\n/background-removal --image ./photo.jpg\n\n# Use remote image\n/background-removal -i https://example.com/photo.jpg\n\n# Auto download result\n/background-removal -i ./photo.jpg --download\n```\n\n### Background Removal Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --image | -i | Target image file or URL | Required |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n| --output | -o | Output directory | Current dir |\n| --download | -d | Auto download result | false |\n\n### Video Enhancement\n\n```bash\n# Basic usage\n/video-enhancement --video ./old-video.mp4\n\n# HD mode\n/video-enhancement -v ./video.mp4 --hd\n\n# With time range\n/video-enhancement -v ./video.mp4 --hd --start 5 --end 15\n\n# Use remote video\n/video-enhancement -v \"https://youtube.com/watch?v=xxx\" --download\n\n# Auto download result\n/video-enhancement -v ./video.mp4 --download\n```\n\n### Video Enhancement Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --video | -v | Target video file or URL | Required |\n| --hd | -h | HD mode (3 credits/sec vs 1 credit/sec) | false |\n| --start | -ss | Start time in seconds | 0 |\n| --end | -e | End time in seconds | Video duration |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n| --output | -o | Output directory | Current dir |\n| --download | -d | Auto download result | false |\n\n### Chat\n\n```bash\n# Simple question\n/chat -m \"Explain Docker in 3 sentences\"\n\n# Multi-turn with streaming\n/chat --messages '[{\"role\":\"system\",\"content\":\"You are a Python expert\"},{\"role\":\"user\",\"content\":\"How to read CSV?\"}]' --stream\n```\n\n### Chat Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --message | -m | Single user message | Required (or --messages) |\n| --messages | -M | Full messages JSON array | Required (or --message) |\n| --model | | LLM model | gpt-4o |\n| --temperature | -t | Sampling temperature (0-2) | Provider default |\n| --max-tokens | | Max response tokens | Provider default |\n| --stream | -s | Enable streaming | false |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n\n### Text-to-Speech\n\n```bash\n# Basic usage\n/tts -t \"Hello, welcome to verging.ai\"\n\n# Choose voice and save to file\n/tts --text \"你好世界\" --voice nova --output ./speech.mp3\n```\n\n### TTS Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --text | -t | Text to convert (max 4096 chars) | Required |\n| --voice | -v | alloy, echo, fable, onyx, nova, shimmer | alloy |\n| --model | | tts-1, tts-1-hd | tts-1-hd |\n| --format | -f | mp3, opus, aac, flac | mp3 |\n| --speed | -s | 0.25 to 4.0 | 1.0 |\n| --output | -o | Save audio file to path | (URL only) |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n\n### Speech-to-Text\n\n```bash\n# Basic usage\n/stt -f ./meeting.mp3\n\n# With language hint\n/stt --file ./interview.wav --language zh\n```\n\n### STT Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --file | -f | Audio file path | Required |\n| --model | | STT model | whisper-1 |\n| --language | -l | Language hint (ISO 639-1) | Auto-detect |\n| --format | | json, text, srt, vtt | json |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n\n### Image Generation\n\n```bash\n# Basic usage\n/imagegen -p \"a cat sitting on a rainbow\"\n\n# High quality, multiple images\n/imagegen --prompt \"product photo of red sneaker\" --quality high --n 2 --output ./images/\n```\n\n### Image Generation Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --prompt | -p | Text description | Required |\n| --model | | gpt-image-1, dall-e-3 | gpt-image-1 |\n| --size | -s | 1024x1024, 1024x1536, etc. | 1024x1024 |\n| --quality | -q | auto, low, medium, high | auto |\n| --n | -n | Number of images (1-4) | 1 |\n| --output | -o | Save images to directory | (URL only) |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n\n### Vision Analysis\n\n```bash\n# Analyze local image\n/vision -i ./screenshot.png -p \"What errors are shown?\"\n\n# Analyze remote image\n/vision --image \"https://example.com/chart.png\" --prompt \"Summarize this chart\"\n```\n\n### Vision Options\n\n| Option | Short | Description | Default |\n|--------|-------|-------------|---------|\n| --image | -i | Image file path or URL | Required |\n| --prompt | -p | Question about the image | Required |\n| --model | | Vision model | gpt-4o |\n| --max-tokens | | Max response tokens | 1024 |\n| --api-key | -k | Your API Key | VERGING_API_KEY env |\n\n### Environment Variables\n\n```bash\n# Set your API Key\nexport VERGING_API_KEY=\"your_api_key_here\"\n\n# Optional: Set API URL (default: https://verging.ai/api/v1)\nexport VERGING_API_URL=\"https://verging.ai/api/v1\"\n```\n\n## Get API Key\n\n1. Visit [https://verging.ai](https://verging.ai)\n2. Register/Login\n3. Click your username in the top right corner\n4. Select **API Keys** from the dropdown menu\n5. Create a new API Key\n\n![API Keys Location](./docs/api-keys-location.png)\n\n## Credits\n\n### Face Swap\n- Normal mode: 1 credit/second\n- HD mode: 3 credits/second\n\n### Background Removal\n- 1 credit per image\n\n### Video Enhancement\n- Normal mode: 1 credit/second\n- HD mode: 3 credits/second\n\n### Chat\n- Post-deduct billing based on token usage\n\n### Text-to-Speech\n- Pre-deduct billing based on character count\n\n### Speech-to-Text\n- Pre-deduct billing based on audio duration\n\n### Image Generation\n- Pre-deduct billing based on model, size, quality, and count\n\n### Vision Analysis\n- Post-deduct billing: 2 base credits + token cost\n\n## License\n\nMIT\n",
  "bytes": 9654,
  "sha": "201b6a7d3570802997506ac3875d8505bf260d365ee9f4c8d592408bff4ef2b0",
  "repo_slug": "verging-ai/agent-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_verging_ai_agent_skills_video_enhancemen_9e4e5f89/readme"
}