transloadit-media-processing
installsforks
How to install transloadit-media-processing?
github/awesome-copilot/transloadit-media-processing
$npx -y skills add github/awesome-copilot --skill transloadit-media-processingProcess media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ pr
SKILL.md
| 1 | # Transloadit Media Processing |
| 2 | |
| 3 | Process, transform, and encode media files using Transloadit's cloud infrastructure. |
| 4 | Supports video, audio, images, and documents with 86+ specialized processing robots. |
| 5 | |
| 6 | ## When to Use This Skill |
| 7 | |
| 8 | Use this skill when you need to: |
| 9 | |
| 10 | - Encode video to HLS, MP4, WebM, or other formats |
| 11 | - Generate thumbnails or animated GIFs from video |
| 12 | - Resize, crop, watermark, or optimize images |
| 13 | - Convert between image formats (JPEG, PNG, WebP, AVIF, HEIF) |
| 14 | - Extract or transcode audio (MP3, AAC, FLAC, WAV) |
| 15 | - Concatenate video or audio clips |
| 16 | - Add subtitles or overlay text on video |
| 17 | - OCR documents (PDF, scanned images) |
| 18 | - Run speech-to-text or text-to-speech |
| 19 | - Apply AI-based content moderation or object detection |
| 20 | - Build multi-step media pipelines that chain operations together |
| 21 | |
| 22 | ## Setup |
| 23 | |
| 24 | ### Option A: MCP Server (recommended for Copilot) |
| 25 | |
| 26 | Add the Transloadit MCP server to your IDE config. This gives the agent direct access |
| 27 | to Transloadit tools (`create_template`, `create_assembly`, `list_assembly_notifications`, etc.). |
| 28 | |
| 29 | **VS Code / GitHub Copilot** (`.vscode/mcp.json` or user settings): |
| 30 | |
| 31 | ```json |
| 32 | { |
| 33 | "servers": { |
| 34 | "transloadit": { |
| 35 | "command": "npx", |
| 36 | "args": ["-y", "@transloadit/mcp-server", "stdio"], |
| 37 | "env": { |
| 38 | "TRANSLOADIT_KEY": "YOUR_AUTH_KEY", |
| 39 | "TRANSLOADIT_SECRET": "YOUR_AUTH_SECRET" |
| 40 | } |
| 41 | } |
| 42 | } |
| 43 | } |
| 44 | ``` |
| 45 | |
| 46 | Get your API credentials at https://transloadit.com/c/-/api-credentials |
| 47 | |
| 48 | ### Option B: CLI |
| 49 | |
| 50 | If you prefer running commands directly: |
| 51 | |
| 52 | ```bash |
| 53 | npx -y @transloadit/node assemblies create \ |
| 54 | --steps '{"encoded": {"robot": "/video/encode", "use": ":original", "preset": "hls-1080p"}}' \ |
| 55 | --wait \ |
| 56 | --input ./my-video.mp4 |
| 57 | ``` |
| 58 | |
| 59 | ## Core Workflows |
| 60 | |
| 61 | ### Encode Video to HLS (Adaptive Streaming) |
| 62 | |
| 63 | ```json |
| 64 | { |
| 65 | "steps": { |
| 66 | "encoded": { |
| 67 | "robot": "/video/encode", |
| 68 | "use": ":original", |
| 69 | "preset": "hls-1080p" |
| 70 | } |
| 71 | } |
| 72 | } |
| 73 | ``` |
| 74 | |
| 75 | ### Generate Thumbnails from Video |
| 76 | |
| 77 | ```json |
| 78 | { |
| 79 | "steps": { |
| 80 | "thumbnails": { |
| 81 | "robot": "/video/thumbs", |
| 82 | "use": ":original", |
| 83 | "count": 8, |
| 84 | "width": 320, |
| 85 | "height": 240 |
| 86 | } |
| 87 | } |
| 88 | } |
| 89 | ``` |
| 90 | |
| 91 | ### Resize and Watermark Images |
| 92 | |
| 93 | ```json |
| 94 | { |
| 95 | "steps": { |
| 96 | "resized": { |
| 97 | "robot": "/image/resize", |
| 98 | "use": ":original", |
| 99 | "width": 1200, |
| 100 | "height": 800, |
| 101 | "resize_strategy": "fit" |
| 102 | }, |
| 103 | "watermarked": { |
| 104 | "robot": "/image/resize", |
| 105 | "use": "resized", |
| 106 | "watermark_url": "https://example.com/logo.png", |
| 107 | "watermark_position": "bottom-right", |
| 108 | "watermark_size": "15%" |
| 109 | } |
| 110 | } |
| 111 | } |
| 112 | ``` |
| 113 | |
| 114 | ### OCR a Document |
| 115 | |
| 116 | ```json |
| 117 | { |
| 118 | "steps": { |
| 119 | "recognized": { |
| 120 | "robot": "/document/ocr", |
| 121 | "use": ":original", |
| 122 | "provider": "aws", |
| 123 | "format": "text" |
| 124 | } |
| 125 | } |
| 126 | } |
| 127 | ``` |
| 128 | |
| 129 | ### Concatenate Audio Clips |
| 130 | |
| 131 | ```json |
| 132 | { |
| 133 | "steps": { |
| 134 | "imported": { |
| 135 | "robot": "/http/import", |
| 136 | "url": ["https://example.com/clip1.mp3", "https://example.com/clip2.mp3"] |
| 137 | }, |
| 138 | "concatenated": { |
| 139 | "robot": "/audio/concat", |
| 140 | "use": "imported", |
| 141 | "preset": "mp3" |
| 142 | } |
| 143 | } |
| 144 | } |
| 145 | ``` |
| 146 | |
| 147 | ## Multi-Step Pipelines |
| 148 | |
| 149 | Steps can be chained using the `"use"` field. Each step references a previous step's output: |
| 150 | |
| 151 | ```json |
| 152 | { |
| 153 | "steps": { |
| 154 | "resized": { |
| 155 | "robot": "/image/resize", |
| 156 | "use": ":original", |
| 157 | "width": 1920 |
| 158 | }, |
| 159 | "optimized": { |
| 160 | "robot": "/image/optimize", |
| 161 | "use": "resized" |
| 162 | }, |
| 163 | "exported": { |
| 164 | "robot": "/s3/store", |
| 165 | "use": "optimized", |
| 166 | "bucket": "my-bucket", |
| 167 | "path": "processed/${file.name}" |
| 168 | } |
| 169 | } |
| 170 | } |
| 171 | ``` |
| 172 | |
| 173 | ## Key Concepts |
| 174 | |
| 175 | - **Assembly**: A single processing job. Created via `create_assembly` (MCP) or `assemblies create` (CLI). |
| 176 | - **Template**: A reusable set of steps stored on Transloadit. Created via `create_template` (MCP) or `templates create` (CLI). |
| 177 | - **Robot**: A processing unit (e.g., `/video/encode`, `/image/resize`). See full list at https://transloadit.com/docs/transcoding/ |
| 178 | - **Steps**: JSON object defining the pipeline. Each key is a step name, each value configures a robot. |
| 179 | - **`:original`**: Refers to the uploaded input file. |
| 180 | |
| 181 | ## Tips |
| 182 | |
| 183 | - Use `--wait` with the CLI to block until processing completes. |
| 184 | - Use `preset` values (e.g., `"hls-1080p"`, `"mp3"`, `"webp"`) for common format targets instead of specifying every parameter. |
| 185 | - Chain `"use": "step_name"` to build multi-step pipelines without intermediate downloads. |
| 186 | - For batch processing, use `/http/import` to pull files from URLs, S3, |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
