In short:
ak-ai-multimodalreads images, PDFs, audio and video, and generates images, video, voice-overs and music. For viewing images and documents, the running model goes first; for generating media or processing audio, it calls the Multix CLI. It never asks for an API key: if one is missing, it names the variable to set and stops.
Disclosure: I maintain AgentKit and have an affiliate relationship with it: the AgentKit link in this post is an affiliate link; buying through it gets you 30% off.
Summary
Use it when you need to pull text or numbers out of an image, transcribe a recording, or generate an image, a short video, a voice-over or background music. There is no need to call an outside service when the running model can already see the file: the skill reads it in the session.
flowchart LR
A["Media file or a request to generate media"] --> B["ak-ai-multimodal"]
B --> C["The running model reads the file"]
B --> D["Multix generates or processes, writes a file"]
B --> E["Stop, name the missing key or capability"]
D --> F["ak-project-organization if files need sorting"]Four concepts to know:
| Concept | Question | Example |
|---|---|---|
| Look with the running model first | Does this need an outside service? | A receipt photo to read: if the model can see, it reads it in the session, no Multix, no key |
| The key must match the job | Which key unlocks which job? | Transcription needs GEMINI_API_KEY, voice and music need MINIMAX_API_KEY |
| Models picked from the current catalog | Which model generates? | It checks the provider's current catalog and pricing and passes a specific model; there is no default model |
| Small test first, check against the source | How do you know the result is usable? | Make a few test images before adjusting one element at a time; check names and numbers in a transcript against the original |
It only checks whether a key is present and never prints its value. A key for one kind of job does not unlock another: an OpenRouter key for images cannot make music.
Sample prompt for transcribing a meeting:
/ak-ai-multimodal <file name>.mp3
Transcribe with timestamps, separate the speakers, mark unclear parts.
Terms to keep exact: <list of terms>.
Save to transcript.md.This skill has no flags.
Below is the detailed version: the run flow, 5 situations with prompts, the change history by ak release, and common pitfalls. The detailed version and the interactive page are for subscribers. Your agent can also search them through the portal's MCP.
Opens when your account has subscriber access
This guide is for subscribers
Once your account has access, the full piece, the interactive visual and the agent call all open.
- Sign in or create a modernEngineer accountReading access belongs to your account email.
- Choose a plan on the pricing page1, 3 or 12 months, paid by VietQR bank transfer. Access opens about a minute after the money arrives.
- Or redeem a Facebook subscriber codePeople supporting the page on Facebook get an activation code by message each month.
Already a subscriber? Sign in to read.
Use this piece in your agent
Get an API keyCopy the text below and paste it into Claude Code, Codex or whichever agent you use. The agent reads the piece and checks it against the repo you have open.
Read "ak-ai-multimodal: read and generate images, audio and video" on modernEngineer and apply it to this repo.
1. Call the content_get tool of the modernengineer MCP server with locale "en", slug "ak-ai-multimodal". If the modernengineer MCP server is not connected, stop and walk me through connecting it from https://modernengineer.dev/en/mcp.
2. Summarize the main steps of the piece and point out which apply to this repo.
3. Propose concrete changes and ask me before editing any file.Connect MCP in Claude Code (once)
claude mcp add --transport http modernengineer \
https://api.modernengineer.dev/mcp \
--header "Authorization: Bearer <API key>"Reading the full piece over MCP needs an API key from a subscriber account or one that bought this guide. Without access, the agent only gets the opening.
- Version
- v1.0.0
- Updated
- 22/10/2026
- Licence
- All rights reserved
- Slug
- ak-ai-multimodal
