Veo 3.1 creates video scenes from text or prepared image frames, with Official and fixed-duration tasks grouped on this page. Official generation offers 4, 6 or 8 seconds, a sound setting and 720p, 1080p or 4K; its image task accepts a starting frame and optional ending frame. The other Veo 3.1 tasks create 8-second clips at those resolutions, and image generation uses exactly two ordered frames. Describe the subject, action, camera and visual details to preserve, then select the task whose input, duration and billing unit match your project.
Veo 3.1 is developed by Google. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Video for a written scene or Image to Video for prepared frames. Use the Official task for its 4/6/8-second duration and sound settings, preparing one or two images for its image workflow. Use the other task for a fixed 8-second request, with two first/last images for image generation. Review the full cost for the selected workflow before submitting.
Google Veo 3.1 Official flagship video model family with Quality, Fast, and Lite tiers featuring cinematic physics, multi-axis camera control, first/last-frame interpolation, synchronized native audio, and 4K workflows.
Google Veo 3.1 Official flagship video model family with Quality, Fast, and Lite tiers featuring cinematic physics, multi-axis camera control, first/last-frame interpolation, synchronized native audio, and 4K workflows.
Google DeepMind's 1080p video model with native audio generation, scene extension to 60+ seconds, and advanced creative controls for cinematic storytelling.
Google DeepMind's 1080p video model with native audio generation, scene extension to 60+ seconds, and advanced creative controls for cinematic storytelling.
A text request describes the whole scene. Official image generation uses one starting image or two first/last images, while the fixed-duration image task requires exactly two. The prompt explains the movement between those states and the camera and geometry to preserve. Keep the selected task’s model identifier and timing fields together when moving from an online test to the API.
| Model / task | Input and workflow |
|---|---|
| Veo 3.1 Official Text-to-Video | Google Veo 3.1 Official flagship video model family with Quality, Fast, and Lite tiers featuring cinematic physics, multi-axis camera control, first/last-frame interpolation, synchronized native audio, and 4K workflows. |
| Veo 3.1 Official Image-to-Video | Google Veo 3.1 Official flagship video model family with Quality, Fast, and Lite tiers featuring cinematic physics, multi-axis camera control, first/last-frame interpolation, synchronized native audio, and 4K workflows. |
| Veo 3.1 Text-to-Video | Google DeepMind's 1080p video model with native audio generation, scene extension to 60+ seconds, and advanced creative controls for cinematic storytelling. |
| Veo 3.1 Image-to-Video | Google DeepMind's 1080p video model with native audio generation, scene extension to 60+ seconds, and advanced creative controls for cinematic storytelling. |
Describe the moving subject, action sequence and camera and use frames when the composition is already prepared. The existing records below show a rainforest flight, rain in a glasshouse, a locomotive arriving between two frames and an observatory’s mechanical opening.
Use the Official text task to specify the animal, flight path, camera and sound setting. The hornbill record asks for a low flight through a misty canopy with wingbeats and rainforest ambience. Inspect the requested movement, environment and sound in the actual clip.
Describe the camera path, moving materials and depth relationships. The fixed 8-second glasshouse record requests a low glide past wet leaves, rain on glass and moving reflections. Review the plant geometry, water and scene depth against the prompt.
Supply compatible first and last images and identify the subject and environment to preserve. The locomotive source establishes the platform, train and dusk lighting before the prompt directs the arrival and final steam-filled view.
In the Official frame task, enable sound and describe the audible events alongside the movement. The train record requests the approaching chug, whistle, brakes and steam release while the locomotive reaches its prepared ending state. Inspect the actual video and sound together.
Use exactly two frames in the fixed-duration image task and explain which connected parts move. The observatory record asks the copper shutters to separate while retaining the dome, stone building, frost and camera. Compare the 8-second result with both endpoints.
The Official example supplies a train’s first and last frames and requests an 8-second 720p arrival with sound enabled. The fixed-duration example supplies the closed and opening observatory states and requests an 8-second 720p mechanical transition. Read the full prompts and compare each pair of source frames with its corresponding actual output, inspecting movement, structure, camera and the requested sound where enabled.
A black steam locomotive rolls into a heritage platform at dusk and slows to a stop, beginning as a distant headlight glow and ending enveloped in thick white steam. Fixed platform-level camera, warm lamp reflections sliding across wet metal. Natural sound: approaching chug, one long whistle, brake squeal, the hiss of released steam. Realistic motion, no text, no logos.
One continuous locked-off shot that moves naturally from the first frame to the second. The copper observatory dome shutters separate slowly and evenly, revealing the dark telescope aperture and a narrow warm interior glow as dawn brightens slightly. Preserve the stone building, dome geometry, mountain silhouette, frost, camera position and composition. Motion should be mechanical, restrained and physically believable. No new objects, no people, no text, no logos, no brands, no products, no advertising, no watermark.
Prepare a written brief for wildlife, weather or narrative motion, or first/last images for an existing visual sequence. Describe the action, camera and preserved details, choose the matching Official or fixed-duration task and review its full estimate. Inspect the output for storyboards, environmental studies, mechanical demonstrations, character scenes or an integrated video workflow.
Write the animal, path, environment and camera, and configure sound in the Official task when needed. Review anatomy, scene continuity and the requested audio for a documentary visual concept.
Describe the material’s movement and camera path, then choose the task and duration. Inspect water behavior, reflections and depth for an environmental scene proposal.
Supply compatible endpoints and explain the movement between them. Review the completed clip against geometry, lighting and the intended final state for a transition concept.
Prepare the frame states and identify hinges, shutters or other moving parts. Keep the camera and surrounding structure defined, then inspect the result for an explanatory animation.
Describe the audible events and their relationship to the action, choose 4, 6 or 8 seconds and select resolution. Review the full sound-tier estimate and inspect the generated shot for a narrative or atmosphere study.
Retain the exact model, prompt, frame URLs and task-specific duration, resolution, framing and sound settings. Submit the authenticated request and track its task ID to retrieve the completed video.
Official tasks are billed per second using the selected resolution, sound setting and 4/6/8-second duration. The other tasks are billed per 8-second video using the selected resolution. The dynamic table keeps each task’s current starting rate and billing unit. Multiply an Official per-second rate by the actual duration, then assess that complete estimate alongside the fixed-video price for the workflow your project needs.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Veo 3.1 Official Text-to-Video | Text to Video | Text prompt | 4K | $0.12 / second | |
| Veo 3.1 Official Image-to-Video | Image to Video | 1–2 image frames | 4K | $0.12 / second | |
| Veo 3.1 Text-to-Video | Text to Video | Text prompt | 4K | $1 / video | |
| Veo 3.1 Image-to-Video | Image to Video | Exactly 2 first/last frames | 4K | $1 / video |
Test your creative brief online, then bring the verified request into your application.
Enter the scene or motion prompt and provide the frame count required by the task. Select resolution and framing; in Official, also select duration and sound. Review the full request estimate, generate and inspect movement, structure, the ending state and any requested audio.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose text or image generation, then Official for its 4/6/8-second and sound controls or the fixed-duration task for 8 seconds. Official image generation accepts one or two frames; the other image task requires two. Select 720p, 1080p or 4K and configure the documented framing.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Review Official duration, resolution and sound together, or the full 8-second price for the fixed-duration task. Use complete request amounts and the planned test count when comparing workflows and budgeting the project.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Veo 3.1 is a Google video family with Official and fixed-duration text and image tasks on Vidgo. Official supports 4/6/8-second clips, sound and one or two image frames; the other tasks use 8 seconds and exactly two frames for image generation. Both task groups provide 720p, 1080p and 4K options.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
