Veo 3
Google DeepMind's groundbreaking video model — the first in the Veo line to offer AI-generated audio alongside cinematic video. Generate stunning clips with synchronized sound in a single pass.
What is Veo 3?
Veo 3 is Google DeepMind's third-generation video model and the original release in the Veo 3 series. It marked a significant milestone as the first Veo model to natively generate AI audio — ambient sound, music, and dialogue-appropriate sound effects — alongside the video clip.
The model produces cinematic-quality video at up to 1080p resolution across 16:9 and 9:16 aspect ratios, making it flexible enough for both landscape and vertical delivery.
For teams building video content workflows, Veo 3 represents a significant step up from earlier generation video models. Its combination of output quality and native audio generation makes it well-suited for social content, brand video, and short-form storytelling.
AI audio generation
Sound, music & FX in same pass
Up to 1080p
720p default, 1080p available
Prompt fidelity
Strong adherence to scene direction
Cinematic output
Google DeepMind quality
How to generate video with Veo 3 on project.video
Open the composer
Access the generation composer from your project.video dashboard. Veo 3 is available alongside all other supported video and image models.
Select Veo 3
Click the model selector and choose Veo 3. Your current prompt carries over — no need to re-enter text when switching between Veo model variants.
Write your prompt
Describe your scene with cinematic intent — camera movement, lighting, subject action, and mood.
Set specs and generate
Choose aspect ratio (16:9 or 9:16), resolution, duration (4s/6s/8s), toggle audio on or off, then generate. View results in your gallery.
Technical specs
Best use cases
Social video with natural sound
Generate a short-form clip with ambient audio — street sounds, nature, music — in one pass. Veo 3 removes the need to source and sync separate audio files for social posts.
Brand storytelling
Cinematic-quality clips at 1080p with the depth and visual richness expected from premium brand content.
Advertising creative
Generate multiple ad concept directions quickly, with synchronized audio and polished visual output in the same pass.
Short-form content at scale
For platforms like Instagram Reels and TikTok, Veo 3's 9:16 support and 4-second format deliver exactly what short-form audiences expect — quickly and at quality.
Example prompts
Copy any of these to get started on project.video.
"Aerial shot of a misty mountain valley at sunrise, golden light breaking over the ridge, birdsong and wind in the audio, slow pan left, 16:9"
"Close-up of a vinyl record spinning on a turntable, warm ambient lighting, needle drop visible, lo-fi jazz audio, shallow depth of field, 16:9"
"Urban street style — person strolls through a crowded marketplace, vibrant stalls, candid energy, vertical format, city audio backdrop, 9:16"