Veo 3.1
Text & image to video · 2025-10
The full-quality model. Use it for final shots: realistic motion, lip-synced dialogue and detailed lighting at up to 1080p, with audio generated alongside the video.
AI video model · By Google DeepMind
Google's Veo 3.1 and Veo 3.1 Fast in your Qten account: cinematic clips with sound, from a prompt or an image.
Free plan · No credit card · Updated 2026-11-18
Veo
By Google DeepMind
2 versions of Veo in one Qten account, from fast drafts to the newest release.
Veo 3.1 is Google DeepMind's AI video model. It turns a text prompt or an image into a short 1080p clip with native audio: dialogue, sound effects and ambience in the same pass. In Qten you can use Veo 3.1 and Veo 3.1 Fast next to 130+ other models.
Veo is Google DeepMind's family of video generation models. Veo 3 added sound generated together with the picture, and Veo 3.1, released in October 2025, improved prompt adherence, audio and image-to-video. It makes clips of 4, 6 or 8 seconds in 16:9 or 9:16, can start from your image, match a first and last frame, and keep a subject consistent with up to three reference images.
| Made by | Google DeepMind |
|---|---|
| Newest on Qten | Veo 3.1 |
| Versions on Qten | 2 |
| Max resolution | Up to 1080p |
| Max length | Up to 8 s |
| Native audio | Yes |
| Reference images | Up to 3 |
| Inputs | Text prompt · Start image · First & last frame · Reference images |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
2 versions of Veo in one Qten account, from fast drafts to the newest release.
Text & image to video · 2025-10
The full-quality model. Use it for final shots: realistic motion, lip-synced dialogue and detailed lighting at up to 1080p, with audio generated alongside the video.
Text & image to video · 2025-10
A faster, lower-cost version of Veo 3.1 with the same 4 to 8 second clips and aspect ratios. Good for testing ideas and drafts before you render the final take.
| Version | What it makes | Tier | Released |
|---|---|---|---|
| Veo 3.1 Fast | Text & image to video | Fast / lower cost | 2025-10 |
| Veo 3.1 | Text & image to video | Standard | 2025-10 |
Dialogue, sound effects and background ambience are generated with the picture, so a clip is ready to watch without separate audio work.
Animate a still, or give a first and last frame and let Veo fill the motion between them.
Add up to three reference images to keep a character, product or style the same across shots.
Generate 9:16 for Shorts, TikTok and Reels, or 16:9 for YouTube, at up to 1080p.
Slow dolly-in on a glass perfume bottle on wet black stone, soft rim light, droplets catching the light, gentle rain sound, 16:9, cinematic.Handheld street interview in a busy Tokyo crosswalk at dusk. A young woman laughs and says: "Honestly? I just follow the noodles." City ambience, 9:16.Aerial drone shot gliding over a misty pine forest at sunrise, birds calling, light rays through the fog, calm and wide, 16:9.Short, polished product shots with sound, ready for paid social.
Characters who speak a line with matching lip movement.
Cinematic B-roll for narrated YouTube videos and Shorts.
Turn a key frame into a moving shot to test an idea fast.
The other video models in the same Qten account. Pick per scene, or let Qten choose.
| Veo | Kling | Seedance | MiniMax Hailuo | Wan | |
|---|---|---|---|---|---|
| Made by | Google DeepMind | Kuaishou | ByteDance | MiniMax | Alibaba |
| Newest on Qten | Veo 3.1 | Kling 4 | Seedance 2.5 | MiniMax H3 | Wan 3 |
| Versions on Qten | 2 | 6 | 7 | 7 | 10 |
| Max resolution | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p |
| Max length | Up to 8 s | Up to 30 s (Kling 4) | Up to 30 s (Seedance 2.5) | Up to 15 s (MiniMax H3) | Up to 30 s (Wan 3) |
| Native audio | Yes | Yes | Yes (Seedance 2.0 / 2.5) | Yes (MiniMax H3) | Yes (Wan 2.5+) |
| Inputs | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · Reference images · Audio | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · Reference images · Audio |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
Sign up on the Free plan. No credit card, and you get credits to start.
Write your prompt or script, then choose Veo as the model, or let Qten pick the best model for each step.
Review the result, edit it in Qten, and post or schedule it to YouTube, TikTok, Instagram and more.
FAQ
Veo 3.1 is Google DeepMind's AI video model, released in October 2025. It makes 1080p clips of up to 8 seconds from text or images, with native audio including dialogue and sound effects.
Qten offers Veo 3.1 and Veo 3.1 Fast. Use Fast for quick, lower-cost drafts and Veo 3.1 for final, highest-quality shots.
Qten has a Free plan with 100 free credits and no credit card. Generating with Veo uses credits; how many depends on the version and clip settings. See the Pricing page for plans and credit packs.
A single Veo 3.1 generation is 4, 6 or 8 seconds long. In Qten you can combine several clips into one longer video with voiceover and captions.
Veo 3.1 is strongest for realistic shots with dialogue and sound in short clips. Kling makes longer clips, up to 30 seconds with Kling 4. Both are in Qten, so you can use each where it fits.
No. You use Veo from your Qten account with Qten credits. There is no separate Google subscription or API key to set up.
Model names and logos are trademarks of their owners. Qten is not affiliated with or endorsed by them.
Veo and 130+ other AI models in one account. Start free.
Start creating free