deapi — Claude Code skill: media tools and installation
Run deAPI tasks from an agent: transcribe audio and video, create images or speech, and extract text from images. Useful when a project needs media processing through commands.
npx skills add deapi-ai/claude-code-skills --skill deapi -a claude-codeWhat deapi does
deapi exposes commands for transcribing video and audio, generating images, speech, and video, reading text from images, removing backgrounds, upscaling, and creating text embeddings. Other commands check the account balance or configure webhook and websocket delivery for server apps.
Set the DEAPI_API_KEY environment variable before using the skill. Requests run asynchronously: deAPI returns a request_id, the agent checks the job status every 10 seconds, then fetches the result from result_url. Results are not delivered as soon as a command starts, so account for the polling step in workflows that need the finished file.
What it helps with
- transcribe audio or video from YouTube, Twitch, Kick, or X
- create an image from a text prompt
- turn text into speech
- extract image text or remove an image background
- create text embeddings for semantic search
Example prompts for the agent
- Transcribe this video with
/transcribe:https://youtube.com/watch?v=.... - Generate an image of a sunset over mountains with
/generate-image. - Turn “Hello world” into speech with
/generate-audioand voiceam_adam.
How to install deapi
1Skills CLI (Vercel)
npx skills add deapi-ai/claude-code-skills --skill deapi -a claude-code2Manually: put the files in place
~/.claude/skills/deapi/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/deapi/
1Skills CLI (Vercel)
npx skills add deapi-ai/claude-code-skills --skill deapi -a codex2Manually: put the files in place
.agents/skills/deapi/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add deapi-ai/claude-code-skills --skill deapi -a cursor2Manually: put the files in place
.cursor/skills/deapi/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install deapi-ai/claude-code-skills deapi2Manually: put the files in place
.github/skills/deapi/SKILL.md1Skills CLI (Vercel)
npx skills add deapi-ai/claude-code-skills --skill deapi -a gemini-cli2Platform CLI
gemini skills install https://github.com/deapi-ai/claude-code-skills --path deapiManually: put the files in place
.devin/skills/deapi/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add deapi-ai/claude-code-skills --skill deapi -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about deapi
How do I install deapi in Claude Code?
Run npx skills add deapi-ai/claude-code-skills --skill deapi -a claude-code. The skill file is at ~/.claude/skills/deapi/SKILL.md.
What does deapi do?
It lets an agent run deAPI tasks for text, images, audio, and video. Commands cover transcription, media generation, image text extraction, and embeddings.
What does deapi need to run?
Set DEAPI_API_KEY in the environment. Jobs are asynchronous: the agent checks their status every 10 seconds before retrieving the result.
Source text
SKILL.md · MIT
--- name: deapi description: AI media generation via deAPI. Transcribe YouTube/audio/video, generate images from text, text-to-speech, OCR, remove backgrounds, upscale images, create videos, generate embeddings. 10-20x cheaper than OpenAI/Replicate. user-invocable: true disable-model-invocation: false --- # deAPI Media Generation AI-powered media tools via decentralized GPU network. ## Available Commands | Command | Use when user wants to... | |---------|---------------------------| | `/transcribe` | Transcribe YouTube, Twitch, Kick, X videos, or audio files | | `/generate-image` | Generate images from text descriptions | | `/generate-audio` | Convert text to speech (TTS) | | `/generate-video` | Create video from text or animate images | | `/ocr` | Extract text from images (OCR) | | `/remove-bg` | Remove background from images | | `/upscale` | Upscale image resolution (2x/4x) | | `/transform-image` | Apply style transfer to images | | `/embed` | Generate text embeddings for semantic search | | `/deapi-setup` | Configure result delivery (webhooks/websockets) for server apps | | `/deapi-balance` | Check account balance and remaining credits | ## Quick Examples ``` /transcribe https://youtube.com/watch?v=... /generate-image a sunset over mountains /generate-audio "Hello world" --voice am_adam ``` ## Setup Requires `DEAPI_API_KEY` environment variable: ```bash export DEAPI_API_KEY=your_key ``` Get your API key at [deapi.ai](https://deapi.ai) (free $5 credit). ## API Pattern All deAPI requests are async: 1. Submit job → get `request_id` 2. Poll status every 10s 3. When `done` → fetch from `result_url` For detailed API parameters, see [docs/api-reference.md](../docs/api-reference.md).
© deapi-ai · MIT · deapi-ai/claude-code-skills
