Voice explanations of code

Ideas Feature Requests
1

Feature request for product/service

Cursor IDE

Describe the request

I’m still a heavy user of the Cursor IDE, generally working on enterprise projects.

We also use Confluence a lot as our knowledge base across the company, and I really love that Confluence pages have a [ Listen ] button at the top, where a modal appears which reads the page for you - so you don’t have to read it yourself. I find myself using this [ Listen ] feature A LOT - as we are in a large company and often need to quickly get up to speed on a lot of different initatives. What I love about this feature though, is it doesn’t just read the exact content of the page - it instead transforms the content into something thats suitable for reading. For example, if there are things like tables or code snippets - instead of reading the table values or reading the code line by line - it instead speaks something thats appropriate - such as summarising some of the key aspects of the table - or explains the code in a more pseudocode manner.

In how frequently I’ve been using that feature in Confluence, when I come back to Cursor in the IDE I find myself wishing I had a similar [ Listen ] button in parts of the IDE. Our organisation has hundreds of repos, and I’m often working in a brand new repo on a weekly basis, and helping contribute to code written by others. I sometimes wish I could have a similar [ Listen ] or [ Explain ] button alongside a file, a function, a type, etc - to quickly get up to speed with what the code is doing - and in a way thats similar to the Confluence one - where its not just reading it out word for word but synthesising / summarising / explaining it.

5

Hey, thanks for the detailed feature request. The Confluence Listen example is really clear, especially the point that it doesn’t read the code word for word, it synthesizes and explains it.

Cursor doesn’t support this yet. Right now, the voice feature is speech-to-text for voice input, not voice output that explains code.

There’s an existing thread in this direction: Text to Speech feature request for reading out generated code and explanations. I’d recommend adding your use case there and calling out the synthesis or summarization part, not verbatim reading. That nuance is what makes your request stand out, and upvotes help with prioritization.

I can’t share an ETA, but the request is clear and useful. If there’s an update, I’ll follow up.

6

Thanks for the response. I just responded to that thread with this use case for consideration on how your team integrates voice features into Cursor.