Text-to-Video
Create dynamic videos from text prompts. Generate engaging visual content without cameras or editing software.
Google's Veo 3.1 Fast for text-to-video. Quick, lower-cost 4, 6 or 8-second clips at 720p or 1080p, landscape or portrait, with dialogue, effects and music in sync with the picture.
Real outputs generated with Veo 3.1 Fast on deAPI.
Video generation
“Japanese macaques sit in a steaming outdoor hot spring surrounded by snowy rocks while snow falls softly, one monkey slowly closes its eyes as snowflakes settle on its fur. Close, eye-level shot with a gentle push-in. Quiet trickle of water and the soft hush of falling snow.” “Japanese macaques sit in a steaming outdoor hot spring surrounded by snowy rocks while snow falls softly, one monkey slowly closes its eyes as snowflakes settle on its fur. Close, eye-level shot with a gentle push-in. Quiet trickle of water and the soft hush of falling snow.”
“Medium close-up of a weathered ship captain in a dark wool coat standing at the wheel on the bridge of a fishing trawler, thick grey fog outside the rain-streaked windows. He narrows his eyes and says in a gravelly voice: "Hold her steady, the harbour lights should be right ahead." Creaking hull, a low foghorn in the distance.” “Medium close-up of a weathered ship captain in a dark wool coat standing at the wheel on the bridge of a fishing trawler, thick grey fog outside the rain-streaked windows. He narrows his eyes and says in a gravelly voice: "Hold her steady, the harbour lights should be right ahead." Creaking hull, a low foghorn in the distance.”
“A blue rally car slides sideways through a tight gravel bend on a forest stage, spraying stones and dust toward the camera, then accelerates away between tall pines. Low trackside camera, slight shake as it passes. Screaming engine, gravel pelting and a turbo whistle.” “A blue rally car slides sideways through a tight gravel bend on a forest stage, spraying stones and dust toward the camera, then accelerates away between tall pines. Low trackside camera, slight shake as it passes. Screaming engine, gravel pelting and a turbo whistle.”
“A hand-drawn 2D anime scene: a schoolgirl with short black hair stands at the railing of a school rooftop at dusk, the wind lifting her hair and scarf as she looks over a city of glowing windows under a pink and violet sky. Slow pan to the right. Cicadas, distant train bells and soft wind.” “A hand-drawn 2D anime scene: a schoolgirl with short black hair stands at the railing of a school rooftop at dusk, the wind lifting her hair and scarf as she looks over a city of glowing windows under a pink and violet sky. Slow pan to the right. Cicadas, distant train bells and soft wind.”
“A single orange tent glowing from within beside a small campfire on a snowy lakeshore, bright green northern lights rippling and swirling across the starry sky above the mountains. Static wide shot on a tripod. Crackling fire and a faint, cold wind.” “A single orange tent glowing from within beside a small campfire on a snowy lakeshore, bright green northern lights rippling and swirling across the starry sky above the mountains. Static wide shot on a tripod. Crackling fire and a faint, cold wind.”
What you can do with Veo 3.1 Fast.
Create dynamic videos from text prompts. Generate engaging visual content without cameras or editing software.
Resolution
720–1920 x 720–1920 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)
Integrate Veo 3.1 Fast 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-fast", "prompt": "a cat walking through a garden", "width": 1280, "height": 720, "frames": 97, "fps": 24 }'{ "model": "veo-3.1-fast", "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.
Other models with similar capabilities you might find useful.
Up to 768×768 resolution. 30–120 frames at 30fps (1–4 sec). Text-to-video and image-to-video modes. Single-step distilled inference.
State-of-the-art video generation model with 22 billion parameters. Supports text-to-video, image-to-video, and audio-to-video with high-quality cinematic output.
Omni-modal 33B video model that generates video and synchronized stereo audio in a single pass. Supports text-to-video and first/last-frame image-to-video, with spoken dialogue in...
Premium model: available after your first top-up.
Quick check before we generate