ai-core/media-generation SKILL.md skillA

ai-core/media-generation from tanstack/ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add tanstack/ai/ai-core/media-generation@git:20261026.ae97655

Pins git:20261026.ae97655 in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

tanstack/ai

Path

packages/ai/skills/ai-core/media-generation/SKILL.md

Versions recorded

20

Latest version

git:20261026.ae97655, committed Oct 26, 2026

First version recorded

Aug 19, 2026

Size

57,659 bytes

Repository stars

3,337

License

MIT

Image, audio, video, speech (TTS), and transcription generation using activity-specific adapters: generateImage() with openaiImage/geminiImage/byteplusImage, generateAudio() with geminiAudio/falAudio, generateVideo() with async polling (openaiVideo/geminiVideo/grokVideo/falVideo/byteplusVideo/openRouterVideo, per-model typed durations), generateSpeech() with openaiSpeech/byteplusSpeech/elevenlabsSpeech, generateTranscription() with openaiTranscription/byteplusTranscription, generateVoice()…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Media Generation

> **Dependency note:** This skill builds on ai-core. Read it first for critical rules.

All media activities (image, speech, transcription, video) follow the same
server/client architecture: a `generate*()` function on the server, an SSE
transport via `toServerSentEventsResponse()`, and a framework hook on the
client.

## Setup -- Image Generation End-to-End

### Server (API route or TanStack Start server function)

```typescript
// routes/api/generate/image.ts
import {
  generateImage,
  generationParamsFromRequest,
  toServerSentEventsResponse,
} from '@tanstack/ai'
import { openaiImage } from '@tanstack/ai-openai'

export async function POST(req: Request) {
  // The hook posts an AG-UI RunAgentInput envelope: the input is in
  // `forwardedProps`, and `threadId` / `runId` are at the top.
  const { input, threadId, runId } = await generationParamsFromRequest(
    'image',
    req,
  )
  if (typeof input.prompt !== 'string') {
    return new Response('Send a text prompt.', { status: 400 })
  }

  const stream = generateImage({
    adapter: openaiImage('gpt-image-1'),
    threadId,
    runId,
    prompt: input.prompt,
    size: '1024x1024',
…

Read the whole file at its exact version.

How to install

mdr add tanstack/ai/ai-core/media-generation@sha256:b2815bde839d4d1c

[![mdr](https://markdownregistry.com/badge/art_koszfhxdvnywlddo.svg)](https://markdownregistry.com/a/art_koszfhxdvnywlddo)

Versions

The registry has recorded 20 versions of this file, between Aug 19, 2026 and Oct 26, 2026, about one every 4 days.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_koszfhxdvnywlddo
GET https://markdownregistry.com/api/v1/resolve?ref=tanstack/ai/ai-core/media-generation
GET https://markdownregistry.com/api/v1/blob/b2815bde839d4d1c1ba34d09953509954175dde60425cd17bddb98c5d32ad0f5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tanstack/ai

Every file in tanstack/ai

Browse by kind, by grade A, or by owner.