Vizard Agent

How to make an audio description track for blind viewers

Last updated 2026-10-10 · 2 min read

Ask Vizard Agent to describe only what is visible: the actions in frame and the changes of shot. It fits that description into the gaps in the existing soundtrack, measures every phrase against the space available, and reads the on-screen titles aloud, because that text is information the audience has no other way to reach.

What do you type into Vizard Agent?

Tell Vizard Agent what to describe and, just as importantly, what to leave alone. The commonest mistake in this format is a description that narrates the plot or repeats something the dialogue has already said perfectly clearly. The word "only" is the whole instruction, because everything audible already reaches the listener.

Make an audio description for this video. Describe only the visual track, the actions in frame and the changes of shot, for blind viewers.

What does Vizard Agent actually do?

Vizard Agent maps the picture and the silence before writing anything. A shot-change map shows where the visual information changes, and the original audio is pulled down separately so its gaps can be measured, because those gaps are the only places a description can go. In the session behind this article it:

When does this not work well?

When there are no gaps. A densely narrated piece with wall-to-wall dialogue leaves nowhere to put a description, and Vizard Agent will tell you which passages have no room. Fast cutting is the other hard case, because the description has to summarise the sequence instead. And it is not a compliance sign-off for broadcast or public-sector accessibility standards.

Common questions

Should it describe the dialogue? No. Only what cannot be heard. Vizard Agent describes the picture alone.

What about on-screen text? It gets read aloud. Vizard Agent reads the titles and credits off the frames.

What if there is no gap? Vizard Agent says which passages have no room rather than talking over the dialogue.