- Veo 3.1
- Veo 3.1 Fast
- Text to video
- Image to video
- Reference to video
Veo 3.1 is Google's video model. It generates sound with the picture: ambience, effects and dialogue. A clip comes back as a scene rather than a silent plate.
In G5 AI Studio you can run Veo 3.1 for final-quality shots and Veo 3.1 Fast for quicker, cheaper drafts, from a prompt, a still or a set of reference images.
Best for
- Dialogue and ambience in one pass
- Social clips that need sound out of the box
- Quick drafts with Veo 3.1 Fast before a final render
Or tell MIRO what you want
MIRO is the AI agent inside G5 AI Studio. Describe the shot in plain language and MIRO picks the model, runs the generations and brings the results back into the chat. It reaches for Veo 3.1 when the shot calls for it.
Chat with MIROHow to prompt it
- Put spoken lines in quotes and say who speaks them.
- Describe the sound you want as plainly as the picture: “rain on a tin roof, distant traffic”.
- Draft with Fast, then rerun the prompt you like on Veo 3.1.
Questions
Does Veo 3.1 make audio?
Yes. Veo 3.1 generates sound together with the video. You can still replace it with your own track or an ElevenLabs voice in the studio.
What is Veo 3.1 Fast for?
Faster, lower-cost generations for exploring an idea. The same prompt can then go to Veo 3.1 for the final take.