Internal + Public

Making music, images and video in chat

VoxBot can generate music, speech, images and video from the chat, at the same prices the studios charge. Every job quotes its price on a confirm card first, and finished media is saved to your gallery.

Updated 2026-11-13 VoxBot Assistant voxbotmusicimagesvideospeechgalleryconfirm-cardcreditsupscalereframe

Ask in plain language

You do not need a command. Describe what you want and VoxBot works out which tool to use, writes the prompt, and shows you what it is about to run.

The confirm card

Every paid job arrives as a confirm card showing the exact credit price before anything runs. You can change your mind, ask for a cheaper model, or ask what the alternatives cost. Nothing is charged until you tap Confirm.

If you want to compare before committing, just ask: VoxBot can quote the live price of a job without starting it.

What it can make

The model catalogue and its prices are the same ones the studios use, so a video from chat costs what the same video costs in Video Studio.

Where the results go

Music, images, video and speech are saved to your gallery. They are yours, they outlive the chat, and you can pull them into any studio afterwards.

Built HTML pages are the exception: they are not saved to the gallery. They live in the chat that made them. See Builds and Finding your files again.

Renders take time

A video is not instant. Most finish in a few minutes, and a longer or higher-resolution take legitimately takes longer. VoxBot will tell you when it is done. If a render fails, nothing is charged, and the result is sometimes delivered late to your gallery anyway, so check there before paying to run it again.