Veo 3.1 Fast Text-to-Video API

google/veo3.1-fast/text-to-video

Generate an 8-second video from a text prompt. Direct the subject, action, setting, camera movement, lighting, and framing, then choose 720p, 1080p, or 4K output.

Input

238/10,000
8sFixed by this endpoint

Output

Idle

Generated video appears here

Configure the input and run the task. Progress and the finished video will stay in this panel.

8s · 720p · 36 credits = $0.180

Examples

One continuous eight-second shot on textured ivory paper. A single black ink drawing of a crane gathers itself, lifts its wings, and rises from the paper as a dimensional ink-wash bird while two loose brush marks trail behind. The camera stays nearly overhead with one gentle push in. Keep the crane silhouette coherent and the ink diffusion restrained. No cuts, no written characters, no readable text, no logos, no brands, no products, no advertising, no watermark.

One continuous eight-second lateral tracking shot along a narrow stone alley just after rain. A fictional adult runner in a plain dark jacket enters from the left, crosses one shallow puddle with a single splash, slows beneath an arch, and exits frame right. Maintain consistent body proportions, foot contact, wet reflections and camera speed. Natural gray daylight, no cuts, no readable signs, no logos, no brands, no products, no advertising, no watermark.

One continuous vertical macro shot of a clear irregular ice cube on dark slate. A warm shaft of sunlight crosses it from top to bottom; the surface beads with water, one droplet slides down, and a small pool grows while caustic light bends across the stone. Fixed camera, physically believable melting and refraction, restrained motion. No cuts, no text, no logos, no brands, no products, no advertising, no watermark.

Veo 3.1 Fast Text-to-Video

Veo 3.1 Fast Text-to-Video turns a written scene into one 8-second video. It is the direct workflow when the shot can be defined without source images. Fast prioritizes a lower credit cost for iteration.

Why Choose This?

  • Start from a written shotCreate motion without preparing source media; describe the visible scene and camera plan in the prompt.

  • Use an explicit endpoint contractThe model ID locks this page to text prompt only, so the form and JSON request stay aligned.

  • Choose the delivery resolutionUse 720p, 1080p, or 4K output with landscape or portrait framing.

  • Budget before submissionThe Playground shows the required credits for the selected resolution before the task is sent.

Parameters

ParameterRequirementDescription
promptRequired

String. Describe visible content, action, camera direction, lighting, and composition; maximum 10,000 characters.

durationOptional

Integer. Defaults to 8; this endpoint accepts no other duration.

Default8
resolutionOptional

String. Select the output resolution; defaults to 720p.

Default720p1080p4k
aspect_ratioOptional

String. Select landscape or portrait framing.

16:99:16

How to Use

  1. Write the sceneDefine the subject, setting, visible action, and the intended progression across one continuous shot.

  2. Direct the motionDescribe concrete subject movement and camera movement in separate clauses so each instruction has a clear role.

  3. Set the outputKeep duration at 8 seconds, then select resolution and aspect ratio.

  4. Run and track the taskSubmit the request, retain task_id, and poll status until the task is finished or failed.

Pricing

Billing is per generated video and depends on the selected resolution.

UsageRateDetails
720p36 creditsPer successful 8-second video request.
1080p36 creditsPer successful 8-second video request.
4k60 creditsPer successful 8-second video request.

Best Use Cases

  • Concept shotsTurn a written visual direction into a short motion concept for review.

  • Campaign variationsGenerate landscape and portrait treatments from the same creative premise.

  • PrevisualizationTest staging and camera movement before committing to production.

Pro Tips

  • Write one coherent shot rather than several unrelated scenes.
  • Separate subject action, camera movement, and visual treatment into clear clauses.
  • Describe only details that can be seen in the finished video.

Notes

  • Generation is asynchronous; keep task_id and stop polling when status reaches finished or failed.
  • The public model ID for this page is veo3.1-fast/text-to-video.

Frequently Asked Questions

Which model ID does Veo 3.1 Fast Text-to-Video use?

Use veo3.1-fast/text-to-video. The Playground keeps this value locked so requests cannot drift into another Veo workflow.

Which duration is supported?

The current Vidgo endpoint accepts a fixed integer duration of 8 seconds.

Which resolutions and aspect ratios are available?

Use 720p, 1080p, or 4k resolution with 16:9 or 9:16 aspect ratio.

Do I need to submit images?

No. image_urls is not accepted by this text-to-video endpoint.

How do I receive the finished video?

The submit call returns task_id. Poll the status endpoint and read the result when status becomes finished; stop on failed.