Google Veo 3.1 and Veo 3.1 Fast
Google's video model with dialogue and sound design made by the model. Run it in Faceless from a prompt.
Updated · By Faceless
Veo is Google's AI video model, and Faceless runs Veo 3.1 and Veo 3.1 Fast
Veo 3.1 turns a prompt into a 4, 6 or 8 second clip at 720p or 1080p, with dialogue, sound effects and ambience when sound is on. An 8 second clip with sound is 48 credits on Veo 3.1 Fast and 128 on Veo 3.1. Type a prompt below and it opens in the Faceless Text to Video studio with the Veo version you pick.
Veo 3.1 or Veo 3.1 Fast: which to use
| Version | Clip length | Resolution | Shapes | Sound | Credits a clip |
|---|---|---|---|---|---|
| Veo 3.1 | 4s, 6s or 8s | 720p, 1080p | 16:9, 9:16 | Optional, costs more | 32 to 128 |
| Veo 3.1 Fast | 4s, 6s or 8s | 720p, 1080p | 16:9, 9:16 | Optional, costs more | 16 to 48 |
- Veo 3.1 Fast to find the shot: the same look and sound in about 1 min, at under half the price.
- Veo 3.1 for the final take, when realism and the sound mix matter most.
Turn sound off for B-roll. Veo prices sound separately, so a clip that will sit under your own voiceover costs less silent: 32 credits on Fast instead of 48.
What Veo costs: 16 to 128 credits a clip
| Veo 3.1 Fast | 4s clip | 6s clip | 8s clip |
|---|---|---|---|
| 720p | 16 / 24 with sound | 24 / 36 with sound | 32 / 48 with sound |
| 1080p | 16 / 24 with sound | 24 / 36 with sound | 32 / 48 with sound |
| Veo 3.1 | 4s clip | 6s clip | 8s clip |
|---|---|---|---|
| 720p | 32 / 64 with sound | 48 / 96 with sound | 64 / 128 with sound |
| 1080p | 32 / 64 with sound | 48 / 96 with sound | 64 / 128 with sound |
The Veo 3.1 tool, which starts from your reference pictures and can extend a clip, is 40 credits a Fast clip and 200 a Quality clip.
Credits come with every plan. Starter is $29 a month for 500 credits, about 10 eight second Veo 3.1 Fast clips with sound. See pricing for the other plans.
Where Veo runs in Faceless
- Text to Video studio. Open Text to Video, pick Veo 3.1 or Veo 3.1 Fast in the Model menu, write the prompt, and set length, resolution, shape and sound. The box above opens it with Veo already picked.
- Veo 3.1 tool. Veo 3.1 makes a clip from your prompt and reference pictures, and Extend carries a finished clip on.
How to write a Veo prompt
- Use film words. Shot size (wide, medium close-up), lens (35mm, macro), light (golden hour, tungsten) and camera move.
- Write the sound. Name the ambience and the effects: "ticking clocks, a soft chime". Veo mixes them under the picture.
- Quote the dialogue. Say who speaks and how: "he says softly, ...". Keep it to a line or two in 8 seconds.
- Name the camera. "Doorbell camera footage, fisheye, night" gets the found-footage look; our AI Santa video guide has two real examples with their prompts.
- Leave things out on purpose. The negative prompt removes what keeps showing up, such as text on screen or extra people.
When another model fits better
For clips longer than 8 seconds, or sound at no extra cost, use Seedance 2.5 (up to 15 seconds). For photoreal people in 1080p up to 15 seconds, use Kling 3.0. They are all in the same studio menu.
Veo questions
Versions, length, sound and credits
Veo is Google DeepMind's AI video model. Veo 3 was the first version to make sound with the picture, and Veo 3.1 is the current one: a prompt in, a short clip with dialogue, sound effects and ambience out. Faceless runs Veo 3.1 and the cheaper Veo 3.1 Fast.
Other models in Faceless
Ready to Create Your Own Videos?
Start creating amazing AI-powered faceless videos in minutes with Faceless
