Browse all Models
Browse all
Browse all
Browse all
  • Text-to-Video
External

Veo 3.1

Google's Veo 3.1 for text-to-video. Cinematic 4, 6 or 8-second clips at 720p or 1080p, landscape or portrait, with dialogue, sound effects and music generated in sync with the picture.

  • Premium model
  • No subscriptions
  • Pay only for what you use

Sample Outputs

Real outputs generated with Veo 3.1 on deAPI.

“Close-up of a late-night radio host in his forties with headphones around his neck, leaning into a large studio microphone in a dim booth lit by a warm desk lamp and glowing ON AIR sign. He smiles and says in a low, calm voice: "It's two a.m., and this one goes out to everyone still awake." Faint hum of the studio, a soft click of a fader.” “Close-up of a late-night radio host in his forties with headphones around his neck, leaning into a large studio microphone in a dim booth lit by a warm desk lamp and glowing ON AIR sign. He smiles and says in a low, calm voice: "It's two a.m., and this one goes out to everyone still awake." Faint hum of the studio, a soft click of a fader.”

“Underwater shot of a green sea turtle gliding slowly over a colourful coral reef, shafts of sunlight rippling through clear blue water, a small school of yellow fish parting around it. The camera drifts alongside at the turtle's level. Muffled ocean ambience and gentle bubbles.” “Underwater shot of a green sea turtle gliding slowly over a colourful coral reef, shafts of sunlight rippling through clear blue water, a small school of yellow fish parting around it. The camera drifts alongside at the turtle's level. Muffled ocean ambience and gentle bubbles.”

“Wide shot of a lone white farmhouse in a golden wheat field as a dark rotating supercell rolls in from the horizon, strong wind bending the wheat in waves, a fork of lightning striking far away. Static camera on a tripod. Howling wind and a long rumble of thunder.” “Wide shot of a lone white farmhouse in a golden wheat field as a dark rotating supercell rolls in from the horizon, strong wind bending the wheat in waves, a fork of lightning striking far away. Static camera on a tripod. Howling wind and a long rumble of thunder.”

“Low tracking shot of three horses galloping along the wet edge of a wide sandy beach at sunset, manes flying, hooves splashing through shallow foam, the low sun flaring behind them. The camera keeps pace from the side. Thundering hoofbeats, splashing water and crashing surf.” “Low tracking shot of three horses galloping along the wet edge of a wide sandy beach at sunset, manes flying, hooves splashing through shallow foam, the low sun flaring behind them. The camera keeps pace from the side. Thundering hoofbeats, splashing water and crashing surf.”

“A stylised 3D animated scene in a cosy cartoon kitchen: a small round white robot with big blue LED eyes flips a pancake high from a frying pan, looks up as it spins in the air, and the pancake lands flat on its head. The robot blinks twice. Sizzling pan, a soft whoosh, a plop and a puzzled little beep.” “A stylised 3D animated scene in a cosy cartoon kitchen: a small round white robot with big blue LED eyes flips a pancake high from a frying pan, looks up as it spins in the air, and the pancake lands flat on its head. The robot blinks twice. Sizzling pan, a soft whoosh, a plop and a puzzled little beep.”

“Extreme macro close-up of a turntable needle lowering onto a spinning black vinyl record, then the camera pulls back smoothly to reveal a small cosy record shop with wooden crates of albums and warm afternoon light. Soft crackle as the needle touches down, then a gentle bossa nova guitar begins to play.” “Extreme macro close-up of a turntable needle lowering onto a spinning black vinyl record, then the camera pulls back smoothly to reveal a small cosy record shop with wooden crates of albums and warm afternoon light. Soft crackle as the needle touches down, then a gentle bossa nova guitar begins to play.”

Capabilities

What you can do with Veo 3.1.

Text-to-Video

Create dynamic videos from text prompts. Generate engaging visual content without cameras or editing software.

Technical Specifications

Resolution

720–1920 x 720–1919 px

Default Size

1280 x 720 px

Inference Steps

1 steps (default: 1)

Guidance

Not required

Video Length

97–193 frames at 24 fps (4–8s)

How to use in deAPI

Integrate Veo 3.1 into your app with a single API call.

POST https://api.deapi.ai/api/v2/videos/generations

curl · deAPI videos/generations

curl -X 'POST' \
  'https://api.deapi.ai/api/v2/videos/generations' \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "veo-3.1",
    "prompt": "a cat walking through a garden",
    "width": 1280,
    "height": 720,
    "frames": 97,
    "fps": 24
}'{
    "model": "veo-3.1",
    "prompt": "a cat walking through a garden",
    "width": 1280,
    "height": 720,
    "frames": 97,
    "fps": 24
}

Tip: The API returns a request_id. Use webhooks (recommended) or poll GET /jobs/{request_id} for results.

Need an API key?

Premium model: available after your first top-up.

Add credits

Frequently Asked Questions

Veo 3.1 is Google DeepMind's video generation model. It turns a text prompt into a single shot with synchronized sound, including spoken dialogue, and is strong on photoreal scenes, natural light and believable motion.
Each clip is 4, 6 or 8 seconds long at 24 frames per second. You can choose 720p (1280×720 landscape or 720×1280 portrait) or 1080p (1920×1080 or 1080×1920). Other lengths and framings, such as square, are not supported.
Yes. Every clip comes with an audio track created in the same pass as the picture: dialogue with matching lip movement, sound effects, ambience and music. Write what should be heard into the prompt, and put spoken lines in quotes.
Price depends only on the length: $0.40 per second, the same at 720p and 1080p. A 4-second clip costs $1.60, a 6-second clip $2.40 and an 8-second clip $3.20. The framing and the prompt do not change it. Call the price endpoint with your exact parameters before committing, and see the partner pricing section at https://deapi.ai/pricing.
Not on deAPI. Veo 3.1 is available here for text-to-video only. To animate a still image, use one of the image-to-video models listed in your /models response.
Partner models run on our partners' infrastructure rather than on deAPI's own GPU network. deAPI acts as the gateway: same unified API, same key, same job flow.
Partner models are not available on the free tier. Make at least one payment to deAPI and your account moves to Premium. The model then appears in your /models response. Until then it is absent from your model list, and calling it by slug returns a plan error.
Make any payment to move your account to Premium, then open the playground and select Veo 3.1, or pass "model": "veo-3.1" to the text-to-video endpoint. See https://docs.deapi.ai for code examples.
  • No subscription
  • Pay only for what you use

Use Veo 3.1 via the deAPI API

Premium model: available after your first top-up.