Media annotations and smart media features
Add comments and link entities from media
- highlight text in PDFs and link content
- add comments to Audio and Video at a certain time
- add comments to images at specific coordinates
- speech-to-text translation
- entity and text recognition in images
- ...
18 Comments
Sign in to comment
In our recent updates, we've now also launched annotations for:
- Weblinks: you can save (desktop-only), highlight, and annotate blog posts, articles, and other websites directly in Capacities. You also get a summary and categories for your weblinks when running AI analysis on them.
- PDFs can now also be highlighted and annotated. This includes text highlights as well as area highlights using our snapshot feature.
Annotation blocks appear in your blocks property in Capacities and can be edited like normal blocks. They just look differently and have some extra features.
With audio recording and audio analysis currently in development, we are nearing the completion of this ticket. If you have any additional requests or ideas, please create a specific ticket for them. Thank you for all your input and ideas on this topic! We hope we can come closer and closer to the vision of Capacities as a Studio for your mind.
Yes, this would be so nice! I am very excited to see its being planned
Would LOVE this! Also voice to text on the ai assistant to have it schedule to-dos would be incredible. I love the usability and interface of Tiimo for to-dos so I've kept it -- but I would switch to capacities if it had voice to text for easy scheduling. I also love how Tiimo automatically adds emojis to make your to do's easier to differentiate (good for ADHD
Meeting Recording - speech-to-text translation and summary (as with Notion AI meeting notes).
This would be so valuable for meeting note taking.
Functionality to export highlighted text and notes is important in my workflow
Please have this! I am a satisfied student that subscribe to your capacities pro and this is one of the feature that I would truly love to have. And please have annotation such as text or maybe in the future to have pencil recognition in the PDF so I can annotate it using my iPad. Honestly really appreciate you guys work and may peace and blessing for all of you!
Would love to see similar support with .epub files. I extensively use this format alongside PDF's and would love to keep everything together in the same app.
Weblinks 2.0 Feature Requests
- "Context" as a Property Type.
Raycast Exension
- "Search Content" result preview always includes the full-url for Weblinks (*not just the domain) that can be selected.
Safari Extension
- Edit Title & Description of Weblink
- Capture Selected Text as a "Highlight"
- Duplication detection for links added via copy & paste and/or via Raycast
- Duplication detection for links with edited titles
Thanks!
pdf pdf pdf edition please !
I would love to again voice my strong support and need for a forward email workflow. I know we can currently send emails to capacities, but the email loses all formatting and often has issues with recognizing links, pictures, attachments, etc. I would like to have all of those get added to a mail object type. I have been waiting since I first started with Capacities 2 years ago and this is still the most needed feature for me to be able to fully use this software to manage my workflows.
Today we launched media analysis for images in early access to all Capacities Believers.
- Full OCR for images
- Dominant color extraction
- Categorization
- Auto-title and image description
- Extracted data available as context in AI chat.
More media types to follow!
With the updates to media types, could we get more customization on weblinks? I'd like to customize properties, categories, and topics. Or remove/hide them all if I wish. The rigidness of weblinks (and most "basic" types) seems strange compared to the wide flexibility of custom types. I understand basic types like daily notes and weblinks have certain inalienable properties, but being able to add more or customize would be nice.
Is there a sneak peak as to what the speech-to-text transcription will include? I'm hoping I can record meetings like WhatsApp calls and other meetings so that I can reference my notes and summarize the meeting within the meeting object. This is the only reason I keep Notion now, and if this feature is launched in Capacities, I can fully move over knowing Notion no longer does anything I need that Capacities doesn't do :)
In addition to adding this internally would be great to have a link from the Highlights app. They have a great system for adding an annotation to a PDF which has the ability to link out to some applications directly, Cap should be on their list of apps.
I agree that email object should be top priority. I have been waiting on it as long as I have been a believer user.
Please move the email object higher up the list
The Email object should be at the top of your list.

As for media - I think it would be just as important to be able to play MP4 and FLAC files.