In iconik, you can add transcriptions and extremely detailed metadata, frame by frame, automatically.
Once you open an asset, you can choose to “analyze” it. This will use AI to recognize every detail in your media such as color, subjects, feelings, and environments.
When the analysis is complete, new tags will be added and instantly searchable. Your videos will also have time-based tags so you can search for an exact frame!
For tags with a low confidence score, you will be able to decide if it's accurate or not.
Out of the box, you can use AI services through iconik. You can also choose to use your own AI license for these services:
Transcriptions can easily be added in iconik using AI to convert voice to text. The text is timestamped, attributed to speakers, and then becomes part of the metadata for that video. This means you can locate a video even if you can only recall part of a spoken phrase.
Speakers are not always clear and AI can occasionally struggle to identify words. Editing text or speaker attributions is a simple and intuitive process.
Once your transcriptions are ready, they can appear as closed captions in the iconik player or be downloaded at text or WebVTT.