Veo 3.1 Lite provides Official text and image generation alongside a fixed 8-second text task on Vidgo. Official supports 720p or 1080p, a sound setting and one starting image or two first/last frames for image generation. At 720p, text and one-image requests can use 4, 6 or 8 seconds; choose 8 seconds for 1080p or a two-frame transition. The other Lite text task uses 8 seconds with 720p, 1080p or 4K. Describe the action and camera, choose the workflow and review its complete per-second or per-video estimate.
Veo 3.1 Lite is developed by Google. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Use Official Text to Video for a written scene or Official Image to Video for prepared first-frame material and an optional ending frame. Match duration to the selected resolution and image count. Choose the other Text to Video task for its fixed 8-second request and resolution tiers, then compare the complete estimate for your intended clip.
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.
Official image generation accepts one or two image_urls, using the second image as the ending frame. Its two-frame workflow uses 8 seconds, as does every Official 1080p request. Official 720p text or single-image requests offer 4/6/8 seconds. The other task describes the whole scene through text and always uses 8 seconds. Keep these conditions with the selected task when preparing the API request.
| Model / task | Input and workflow |
|---|---|
| Veo 3.1 Lite 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 Lite 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 Lite 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. |
Describe the moving parts, camera and details to preserve, then choose a timing supported by the task. The existing records below show a skateboard action, latte art, a guitarist animated from one image, a lantern transition and wind moving across a hillside.
Use Official text generation to identify the subject, camera and sound setting. The morning-ollie record asks for a skateboard jump with the tail snap, landing wheels and distant sprinkler. Inspect the actual movement and audio against the prompt.
At Official 720p, choose a supported 4-second request for a concise action. The latte record asks milk to pour into espresso and form a rosetta under a macro camera. Inspect flow, surface pattern and the requested restrained movement.
Supply the source image and describe the body, object and environmental movement. The campfire-guitarist record asks for strumming, sparks and changing firelight with guitar and night sounds. Compare appearance and instrument structure with the source.
Provide first and last images and choose 8 seconds for the Official two-frame workflow. The lantern record changes the light from its opening state to a warm amber glow while the paper shade sways. Inspect the ending state, structure and lighting against both frames.
Use the fixed 8-second text task to define the direction, material and camera. The hillside record asks one gust to travel from far left to near right through tall grass. Review the wave, stable horizon and scene continuity for an environmental concept.
The first record supplies a lantern’s first and last frames and requests an 8-second 720p Official transition with sound disabled. The second uses text to request an 8-second 720p wave of wind across a grassy hillside. Read the full prompts, compare the lantern frames with the actual transition and inspect the written movement in the hillside result.
A paper lantern hanging in a quiet dusk alley flickers alive and settles into a warm amber glow, swaying subtly in a light breeze, shadows softening on the wall behind it. Calm, realistic motion, no text, no logos.
One continuous eight-second locked-off shot across a hillside of tall green grass under soft overcast light. One broad gust travels clearly from the far left to the near right, bending the grass in a single coherent wave before it rises again. Natural wind physics, stable horizon, restrained documentary color. No people, no buildings, no text, no logos, no brands, no products, no advertising, no watermark.
Write a short physical or environmental action, supply one image for a prepared subject or two frames for a defined transition. Select the supported Lite task, resolution, duration and Official sound setting, then inspect the video for storyboards, character presentations, material studies, atmospheric scenes or an integrated video workflow.
Describe the subject, movement and camera and configure the Official sound setting when needed. Review anatomy, contact and sound events for a character or storyboard concept.
Write the pour, surface change or other small action and choose a supported duration. Inspect the generated motion and texture for a material or visual presentation.
Provide one image to Official Image to Video and describe movement and the appearance to retain. Review the source and result for identity, structure and coordinated light.
Prepare two compatible images and use the 8-second Official frame workflow. Explain the change and preserved surroundings, then inspect the result against both endpoints.
Describe the weather, natural material and stable camera for the fixed 8-second text task. Review motion and spatial continuity for an environmental storyboard or visual study.
Retain the exact model, prompt, image URLs and the matching resolution, duration, framing and sound settings. Submit the authenticated request and track its task ID to retrieve the result.
Lite Official tasks are billed per second according to 720p or 1080p, sound and the supported duration. The other Lite text task is billed per 8-second video at its selected resolution. The dynamic table shows each task’s current starting rate and billing unit. Use the actual resolution, frame count and duration to review the full estimate and plan the number of tests for your project.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Veo 3.1 Lite Official Text-to-Video | Text to Video | Text prompt | 1080p | $0.018 / second | |
| Veo 3.1 Lite Official Image-to-Video | Image to Video | 1–2 image frames | 1080p | $0.018 / second | |
| Veo 3.1 Lite Text-to-Video | Text to Video | Text prompt | 4K | $0.1 / video |
Test your creative brief online, then bring the verified request into your application.
Enter the prompt and the required image frames, then choose the resolution and a duration allowed by that combination. Configure Official sound and framing where supported. Review the full estimate, generate and inspect action, source appearance, structure, lighting and the requested ending state.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Official text or image generation for 720p/1080p and sound controls, preparing one or two images for the image task. Use 8 seconds at 1080p or with two frames; Official 720p text and one-image jobs can use 4/6/8 seconds. Choose the other text task for 8 seconds at 720p, 1080p or 4K.
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 the Official per-second rate with its actual duration and sound, or the full 8-second price for the other text task. Include the planned test count when budgeting the supported output specification.
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 Lite is a Google video variant with three Vidgo tasks: Official Text to Video, Official Image to Video and a fixed 8-second Text to Video task. Official uses 720p or 1080p, sound and task-specific 4/6/8-second conditions. The other text task offers 720p, 1080p or 4K at 8 seconds.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
