generateVideo

function generateVideo<TAdapter, TStream>(options): TStream extends true ? AsyncIterable<AGUIEvent, any, any> : Promise<VideoJobResult>;

Defined in: packages/ai/src/activities/generateVideo/index.ts:413

Generate video - creates a video generation job from a text prompt.

Uses AI video generation models to create videos based on natural language descriptions. Unlike image generation, video generation is asynchronous and requires polling for completion.

When stream: true is passed, handles the full job lifecycle automatically: create job → poll for status → stream updates → yield final result.

Type Parameters

TAdapter

TAdapter extends VideoAdapter<string, any, any, any, any, any>

TStream

TStream extends boolean = false

Parameters

options

VideoCreateOptions<TAdapter, TStream>

Returns

TStream extends true ? AsyncIterable<AGUIEvent, any, any> : Promise<VideoJobResult>

Examples

Create a video generation job

import { generateVideo, getVideoJobStatus } from '@tanstack/ai'
import { openaiVideo } from '@tanstack/ai-openai'

// Start a video generation job
const { jobId } = await generateVideo({
  adapter: openaiVideo('sora-2'),
  prompt: 'A cat chasing a dog in a sunny park',
  threadId,
})

console.log('Job started:', jobId)

// The submission only OPENS the run; the poll that sees a terminal state is
// what completes it. The `jobId` is the whole correlation — pass the same
// `middleware` and `threadId` when you use them.
const status = await getVideoJobStatus({
  adapter: openaiVideo('sora-2'),
  jobId,
  threadId,
})

Stream the full video generation lifecycle

import { generateVideo, toServerSentEventsResponse } from '@tanstack/ai'
import { openaiVideo } from '@tanstack/ai-openai'

const stream = generateVideo({
  adapter: openaiVideo('sora-2'),
  prompt: 'A cat chasing a dog in a sunny park',
  threadId,
  stream: true,
  pollingInterval: 3000,
})

return toServerSentEventsResponse(stream)