What exactly does Video Intelligence analyze?
Pics.io AI analyzes the entire video, not just the thumbnail. It picks up spoken words (and turns them into a transcript), recognizes scenes, objects, people, brands, events, actions, and even on-screen text (OCR). On top of that, it creates short summaries and chapters with timestamps, so you can quickly jump to the part you actually need.
Do I need to tag videos manually?
Not unless you want to. AI automatically handles transcripts, tags, entities, and chapters. Manual tags are there for your own business context — projects, campaigns, internal labels, versions, and so on. In practice, most teams combine both: use AI metadata to find the right clip, then narrow it down with your own custom fields.
Does it work with large video libraries?
Yes. Video Intelligence was built with big libraries in mind. It works with assets stored in Google Drive, Amazon S3, or your own storage. Videos are processed in the background, and all metadata goes straight into your Pics.io DAM — no extra copying or moving files around.
Does it support multiple languages?
Yes, transcription, OCR, and tagging support a wide range of major languages. If you work with multilingual content, the AI processes each recording in its original language and generates metadata to match, so you don’t have to standardize everything first.
Will users see only the videos they have permission for?
Exactly. Video Intelligence follows the same permission rules you already use in Pics.io. People can only search and see metadata for videos they’re allowed to access. There’s no need to re-upload anything or create duplicate libraries — your assets stay where they are, with the same access levels.
Can I search inside transcripts and on-screen text?
Yes. You can search across transcripts, OCR, AI tags, brands, people, and events in one go. Type a phrase, topic, name, or keyword, and jump straight to the exact moment in the video where it appears.
Which plans include Video Intelligence?
Video Intelligence is included in the AI Kit add-on, together with our AI tools for images. Higher tiers simply raise your processing limits and are better suited for very large libraries. For exact limits and pricing, check the pricing page.
Can we access Video Intelligence results via API?
Yes. If your platform or marketplace handles a lot of user-generated video, you can call Video Intelligence via API. Your system can trigger analysis, then reuse the generated tags, entities, and transcripts in your own UI, search, or recommendations.