Insights are what ioMoVo extracts from an asset when it processes it: the text, topics, objects and structure that turn a file into something you can search by content rather than by filename.

This is the difference between a library that answers "find Q3_final_v2.mp4" and one that answers "find the clip where someone mentions the new facility".

Select the file, choose the index option, review the advanced options, and start. The advanced options are worth a look rather than a click through: they control what gets extracted, how deeply the content is analyzed, and which models are applied. The right settings depend on what you plan to do with the asset.

You can also generate insights while looking at an asset, which is the quicker route when you have already opened something and realised it has not been processed.

For a library rather than a file, select the set and process them together. This is what you want for a first pass over existing content.

Video and audio go through the same process and produce insights suited to time based media, so you can find a moment inside a file rather than just identifying the file.

Once processing finishes, open the file preview. Everything extracted is available there, and it is also what your searches run against from that point on.

The models you have connected. Insights can only do what your connected models support. If something you expect is missing, check your model setup before assuming the process failed.

The options you chose at the start. Assets processed with minimal settings produce minimal insights. You can run an asset again later with better settings, so a first pass does not lock you in.

Run a representative sample before a full library pass. You will see what the output actually looks like against your own content, and because processing bills to your own model keys, you will also learn what a full run costs. Both are much easier to act on beforehand.

Connecting your own AI models covers model setup. Sending files for indexing covers the wider process. Transcription and captions and Translating insights cover the language side.