Playground | veo4api

Playground/fal-ai/veo4/text-to-video

Veo 4 1.0

Drop a prompt below or pick a starting point. Every submission runs live against the model.

Veo 41.0

Runs against fal-ai/veo4/text-to-video via server proxy

Integration

Ship Veo 4 into your own stack.

The playground above is the same endpoint you call in production. Below, three canonical code paths and the full input reference. Copy what matches your stack.

Endpointfal-ai/veo4/text-to-videovideo

TypeScript · @fal-ai/client

1import { fal } from "@fal-ai/client";
2
3fal.config({ credentials: process.env.FAL_KEY });
4
5const { data } = await fal.subscribe("fal-ai/veo4/text-to-video", {
6  input: {
7    "prompt": "A documentary style street interview at night. Person looks at the camera and sa...",
8    "safety_tolerance": 3,
9    "auto_fix": false,
10    "duration": "8s",
11    "aspect_ratio": "16:9",
12    "resolution": "1080p",
13    "generate_audio": true
14  },
15  logs: true,
16});
17
18console.log(data);

Python · fal-client

PYTHON

1import fal_client
2
3result = fal_client.subscribe(
4    "fal-ai/veo4/text-to-video",
5    arguments={
6      "prompt": "A documentary style street interview at night. Person looks at the camera and sa...",
7      "safety_tolerance": 3,
8      "auto_fix": false,
9      "duration": "8s",
10      "aspect_ratio": "16:9",
11      "resolution": "1080p",
12      "generate_audio": true
13    },
14    with_logs=True,
15)
16
17print(result)

HTTP · queue.fal.run

BASH

1curl -X POST "https://queue.fal.run/fal-ai/veo4/text-to-video" \
2  -H "Authorization: Key $FAL_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{ "prompt": "A documentary style street interview at night. Person looks at the camera and sa...", "safety_tolerance": 3, "auto_fix": false, "duration": "8s", "aspect_ratio": "16:9", "resolution": "1080p", "generate_audio": true }'

Input parameters

Key	Kind	Default	Options
prompt	text (required)	—	Primary generation input
duration	select	8s	4 seconds, 6 seconds, 8 seconds
aspect_ratio	select	16:9	16:9 landscape, 9:16 portrait, 1:1 square
resolution	select	1080p	720p, 1080p, 4K
generate_audio	select	true	Native audio on, Silent render
safety_tolerance	default	3	Sent with every request unless overridden.
auto_fix	default	false	Sent with every request unless overridden.

Full, authoritative schema at fal.ai/models/fal-ai/veo4/text-to-video/llms.txt.