# Veo 3.1 Text-to-Video (Async)

> Veo 3.1 Text-to-Video (Async) is a paid API for AI agents from fal.ai (queue) at fal-queue.mpp.tempo.xyz, paid per call via MPP, price unknown, status unknown (last checked 2026-10-30).

Generates video clips from text prompts using Google's Veo 3.1 model, submitted asynchronously via fal.ai's queue for jobs exceeding typical sync timeouts.

## Facts

- Endpoint: POST https://fal-queue.mpp.tempo.xyz/fal-ai/veo3.1?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Provider: fal.ai (queue)
- Docs: https://fal.ai
- Website: https://fal.ai
- Tags: ai, media
- Canonical page: https://www.zero.xyz/c/fal-ai-queue-veo-3-1-text-to-video-async-26a3a6b3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_U0PlpKpNv5SuTiIPmZ6Dz

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability fal-ai-queue-veo-3-1-text-to-video-async-26a3a6b3 -d '<json body>'
```

Example prompt: Can you generate a short video of a golden retriever playing fetch on a sunny beach at sunset, cinematic style — use Veo 3.1 for this?

## When to prefer this

Choose this endpoint when you need high-quality AI video generation from text using Google's Veo 3.1 model and can tolerate async/batch latency. Prefer it over synchronous endpoints when video generation is expected to exceed ~100 seconds. Ideal for creative, marketing, or educational video content production where quality matters more than immediate turnaround.

## Known failure modes

- Prompt too vague or violates content policy — generation rejected
- Queue timeout if polling is not implemented correctly
- Dynamic pricing may lead to unexpected cost if model demand is high
- Video generation fails due to model-side error, returning error status on poll
- request_id lost before polling completes, result unrecoverable without it

## How this service works

Veo 3.1 - text-to-video (async, dynamic pricing)

## Output

The endpoint immediately returns a request_id upon submission. The agent must poll fal.ai's queue status endpoint with that request_id to check job progress, and upon completion receives a URL to the generated video file.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fal-ai-queue-veo-3-1-text-to-video-async-26a3a6b3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fal-queue.mpp.tempo.xyz](https://www.zero.xyz/host/fal-queue.mpp.tempo.xyz/llms.txt)