Cinematic video with sound from text or key frames.
Veo 3.1 is available in IIshki Studio — video generation from a prompt, paid for with tokens. IIshki club members get reduced prices on every model. Pick a model above, set the parameters and start the generation.
Veo 3.1 is Google's video generation model: it creates clips with sound built in, from a text prompt or from a starting frame. It is known for its cinematic image and for handling spoken dialogue, which makes it a strong pick for videos that need a voice and an atmosphere.
Veo 3.1 generates video with sound built in, either from a text prompt or from a starting frame, in 16:9 and 9:16. Its strengths are cinematic quality and support for speech on screen.
Yes — Veo 3.1 produces video with audio already baked in. That is its key difference from most video models, where sound has to be added in a separate step.
The price is shown in tokens (1 token = 1 ₽) on the model card in IIshki Studio. Tokens can be bought without a subscription, and club members get a separate, lower club price.