Veo 3 is Google's AI video model that makes the picture and the sound together, and Veo 3.1 is its update. Solmi runs Veo 3.1 Fast as the Premium tier of its AI video generator, and this page opens the tool with it selected. Describe a scene, pick 4, 6, or 8 seconds at 720p or 1080p in 16:9 or 9:16, and get a clip with sound effects, ambience, and any lines of dialogue you write. It costs 12 credits a second at 720p (48 for 4 seconds) and 15 at 1080p, and a 4-second clip takes about a minute.
From a written prompt to a Veo 3.1 clip with sound in three steps.
Veo is Google DeepMind's family of video models. Veo 3 was the first Veo model to generate sound together with the picture, from footsteps and weather to spoken lines, and Veo 3.1 follows prompts more closely and makes richer sound. Veo 3.1 Fast is the quicker, cheaper variant, and it is the version Solmi runs, with sound always on.
Write the shot like a short script: who is in it, where, what happens, and how the camera moves. Then add the sound: name the effects and the ambience, and put a line of dialogue in quotes with who says it. Keep to one action per clip, since 8 seconds goes fast, and leave on-screen text out. For a music video shot, describe the scene and not the song: Veo's sound will not follow your track.
Solmi runs Veo from a written prompt only: to start from a photo, use image to video, whose tiers run other models. Clips stop at 8 seconds and 1080p; to make one longer, continue it with the video extender. The sound is generated for the scene and does not follow your song; for a performance lip-synced to your track, use the AI music video generator. Solmi is independent of Google and not affiliated with it: it runs Veo 3.1 Fast through Google Cloud and prices it in Solmi credits.
No. The shortest Veo 3.1 clip, 4 seconds at 720p, costs 48 credits, an 8-second clip 96, and 120 at 1080p, shown before you generate. New accounts start with 20 credits, which covers a short Standard-tier clip but not a Veo one; for Veo, add credits with a paid plan or a credit pack.
Veo 3.1 Fast, the quicker Veo 3.1 model, with sound on. It is the Premium tier of Solmi's AI video generator, which turns a written prompt into a clip.
About a minute for a 4-second clip at 720p. An 8-second clip or 1080p takes a little longer, usually under two minutes. For quick, cheaper drafts, use the Standard tier.
Yes. Solmi asks Veo to generate audio with every clip: sound effects, ambience, and any dialogue you write in quotes. The sound does not follow your song, so for a music video put your own track over it.
4, 6, or 8 seconds, at 720p or 1080p, in 16:9 or 9:16. At 720p it costs 12 credits a second and at 1080p 15, so 48 to 96 credits at 720p and 60 to 120 at 1080p.