# Text to Speech feature request for reading out generated code and explanations

**URL:** <https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000>\
**Category:** Feature Requests\
**Created:** [October 15, 2024, 3:46pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000 "2024-10-15T15:46:46Z")\
**Posts on this page:** 18\
**Page:** 3

<div class="post-metadata">

**Author:** ![andresreibel](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/andresreibel/32/4864_2.png) [@andresreibel](https://forum.cursor.com/u/andresreibel)\
**Post date:** [January 3, 2025, 6:40pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/41 "2025-01-03T18:40:11Z")

</div>

Hey, I would be a lot faster if I could just speak to the a composer/chat and it translates the speech to words.

---

<div class="post-metadata">

**Author:** ![ilpoleppanen](https://avatars.discourse-cdn.com/v4/letter/i/c89c15/32.png) [@ilpoleppanen](https://forum.cursor.com/u/ilpoleppanen)\
**Post date:** [January 10, 2025, 7:19am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/42 "2025-01-10T07:19:56Z")

</div>

I guess you’re referring to STT (speech-to-text) instead? Being able to speak your prompt instead of typing?

→ Definitely needed! Though, there are external solutions and applications to this, or you could even build your own in the meanwhile - best of those are platform-specific however (Apple)..

---

<div class="post-metadata">

**Author:** ![andresreibel](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/andresreibel/32/4864_2.png) [@andresreibel](https://forum.cursor.com/u/andresreibel)\
**Post date:** [January 10, 2025, 3:17pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/43 "2025-01-10T15:17:50Z")

</div>

Well really, TTS (model-to-user) and STT (user-to-model): I would like to have a conversation with the agent. In a sense, I think a key metric for cursors success is the split between the agent window and the code window. The smaller the code window per unit of time spent, the better cursor works.

For example, I would like to talk to the AI while I am traveling. Plan out the app, check implementation variations, run tests etc. Then when I come back to the laptop, I have a summary of what was discussed: a nicely organized dashboard. So then I can simply hammer out the various approaches on the laptop.

The TTS-STT is needed because a) I can’t type the complex instructions into my mobile when afk and b) I program now in language so no need for the precision - I need speed and language is faster than typing (and more convenient).

Just think of it like the OpenAI real time API with a great code interface and dashboard.

---

<div class="post-metadata">

**Author:** ![cursmop](https://avatars.discourse-cdn.com/v4/letter/c/e68b1a/32.png) [@cursmop](https://forum.cursor.com/u/cursmop)\
**Post date:** [February 28, 2025, 9:14pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/44 "2025-02-28T21:14:37Z")

</div>

I would like to implement a screen reader (TTS) if I can have an API (or even just applescript) access for that. Any interest?

---

<div class="post-metadata">

**Author:** ![jacques-kigo](https://avatars.discourse-cdn.com/v4/letter/j/a698b9/32.png) [@jacques-kigo](https://forum.cursor.com/u/jacques-kigo)\
**Post date:** [July 7, 2025, 2:41pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/45 "2025-07-07T14:41:35Z")

</div>

I’ve been using SuperWhisper flawlessly for this and can highly recommend it.

---

<div class="post-metadata">

**Author:** ![Saurabh\_Dhir](https://avatars.discourse-cdn.com/v4/letter/s/e8c25b/32.png) [@Saurabh\_Dhir](https://forum.cursor.com/u/Saurabh_Dhir)\
**Post date:** [August 25, 2025, 5:15am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/46 "2025-08-25T05:15:05Z")

</div>

### Feature request for product/service

Chat

### Describe the request

Hi team,

I’d like to request a speech-to-text feature in the chat window. The idea is to allow users to speak their prompts instead of typing, and have Cursor automatically convert the speech into text.

This would be extremely helpful in situations where:

A user has an injury or temporary limitation (for example, my left hand is currently fractured, and typing long prompts is slow and painful).

Users want to quickly jot down thoughts or ideas verbally without breaking their flow.

Accessibility needs, making Cursor more inclusive for people who have difficulties with typing.

The integration could be as simple as a microphone button next to the input box, allowing users to toggle voice input when required. Many platforms (Google Docs, mobile keyboards, etc.) already provide similar functionality, and bringing it into Cursor would make the chat experience much smoother and accessible.

I believe this feature would significantly improve usability, accessibility, and productivity for many Cursor users.

Thanks,  
Saurabh Dhir

---

<div class="post-metadata">

**Author:** ![ckizer](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/ckizer/32/21728_2.png) [@ckizer](https://forum.cursor.com/u/ckizer)\
**Post date:** [January 23, 2025, 5:52pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/47 "2025-01-23T17:52:42Z")

</div>

**New Title Suggestion: “Revolutionize Text Input with Whisper Dictation”**

Imagine hands-free text entry that’s not only fast, but incredibly accurate. Whisper’s cutting-edge voice dictation technology, powered by OpenAI, offers a superior alternative to the standard built-in speech-to-text solutions. With its ability to handle complex vocabulary and provide greater accuracy, Whisper can truly transform the way we interact with our favorite editor. I’m asking the Cursor team to consider integrating support for Whisper dictation.

**Why this feature matters:**

• **Unmatched Accuracy:** Whisper outperforms traditional dictation tools, significantly reducing the need for corrections.

• **Flexibility and Choice:** Users could either access OpenAI’s Whisper API or connect a locally hosted Whisper model, depending on their preferences and workflow.

**What I’m requesting:**

1. Seamless integration of OpenAI’s Whisper API for top-tier dictation capabilities.

2. Support for locally hosted Whisper models, providing more options for privacy-conscious users.

Let’s bring unparalleled voice-to-text performance to our editor and make text entry effortless and precise!

**Mockup**

 ![CleanShot 2025-01-23 at 12.48.47@2x](https://us1.discourse-cdn.com/cursor1/original/3X/2/4/2414e9bf53c465a9534e2ffda2a4c95ead8f15b8.jpeg)

---

<div class="post-metadata">

**Author:** ![masgpt](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/masgpt/32/38497_2.png) [@masgpt](https://forum.cursor.com/u/masgpt)\
**Post date:** [February 10, 2025, 4:17am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/48 "2025-02-10T04:17:11Z")

</div>

I just found the dictation tool in Cursor, and it’s not half bad.

cmd+opt+v

It works in a document, like .md or notes, but it doesn’t work in the compose,r which it should just be added.

---

<div class="post-metadata">

**Author:** ![temp-sunsetmango](https://avatars.discourse-cdn.com/v4/letter/t/e19b73/32.png) [@temp-sunsetmango](https://forum.cursor.com/u/temp-sunsetmango)\
**Post date:** [February 10, 2025, 4:25am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/49 "2025-02-10T04:25:55Z")

</div>

Use macwhisper

TON OF FEATURE REQUESTS COULD BE ADDED

TON OF STUFF THESE GUYS CAN BUILD

SO FAR THEY’VE ONLY BEEN ABLE TO COME UP WITH COMPOSER

HAHA

---

<div class="post-metadata">

**Author:** ![martinopensky](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@martinopensky](https://forum.cursor.com/u/martinopensky)\
**Post date:** [April 4, 2025, 12:04pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/50 "2025-04-04T12:04:11Z")

</div>

I didn’t manage to find this feature in Cursor. Is it still there?

---

<div class="post-metadata">

**Author:** ![martinopensky](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@martinopensky](https://forum.cursor.com/u/martinopensky)\
**Post date:** [April 4, 2025, 12:06pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/51 "2025-04-04T12:06:00Z")

</div>

I have built my own integration, which allows local Whisper transcription as well as using Open AI and Grok APIs for online transcription. I will be releasing an update soon and can update here as well if you’re interested. It works pretty well on Mac M1 local!

---

<div class="post-metadata">

**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\
**Post date:** [April 4, 2025, 6:06pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/52 "2025-04-04T18:06:09Z")

</div>

Hey, this feature is not available in Cursor yet, but it might be added in the future. We are considering the implementation of new features that users request, so what you are doing here is very helpful.

---

<div class="post-metadata">

**Author:** ![martinopensky](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@martinopensky](https://forum.cursor.com/u/martinopensky)\
**Post date:** [April 25, 2025, 12:41pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/53 "2025-04-25T12:41:52Z")

</div>

I have made a big release for this VSCode extension and it’s working great for me with Cursor on a Mac M1.

> **[GitHub - martin-opensky/whisper-assistant-vscode: Whisper Assistant is a powerful VSCode extension...](https://github.com/martin-opensky/whisper-assistant-vscode)**
>
> Whisper Assistant is a powerful VSCode extension that allows developers to use their voice to develop software. Speech can be transcribed locally using the Whisper model or remotely using an API such as OpenAI's. By combining this capability with Cursor developers can quickly develop software using their voice to prompt AI models.

> **[Whisper Assistant - Visual Studio Marketplace](https://marketplace.visualstudio.com/items?itemName=MartinOpenSky.whisper-assistant)**
>
> Extension for Visual Studio Code - Leveraging OpenAI's Whisper to transcribe your speech, enhancing your coding efficiency and experience.

It would be great to get some feedback from the Cursor team @deanrie!

---

<div class="post-metadata">

**Author:** ![martinopensky](https://avatars.discourse-cdn.com/v4/letter/m/3be4f8/32.png) [@martinopensky](https://forum.cursor.com/u/martinopensky)\
**Post date:** [April 25, 2025, 12:44pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/54 "2025-04-25T12:44:23Z")

</div>

For local transcription only SoX and Docker is required to get started and with a Mac M1 the transcription speed is much faster than previous versions of the extension.

Support for remote transcription through the OpenAI and Groq APIs is also included in this release for those lacking the machine power to support local transcription.

---

<div class="post-metadata">

**Author:** ![valentinoPereira](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/valentinopereira/32/78806_2.png) [@valentinoPereira](https://forum.cursor.com/u/valentinoPereira)\
**Post date:** [August 25, 2025, 7:42am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/55 "2025-08-25T07:42:56Z")

</div>

Cursor should buy this from you already 😉

---

<div class="post-metadata">

**Author:** ![Oleksandr\_Dohtiev](https://avatars.discourse-cdn.com/v4/letter/o/d2c977/32.png) [@Oleksandr\_Dohtiev](https://forum.cursor.com/u/Oleksandr_Dohtiev)\
**Post date:** [April 21, 2026, 8:48pm UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/56 "2026-04-21T20:48:04Z")

</div>

_+1 for TTS on assistant responses (speaker icon per message, like ChatGPT). Would love to hear answers instead of only reading them._

---

<div class="post-metadata">

**Author:** ![Nattawat](https://avatars.discourse-cdn.com/v4/letter/n/22d042/32.png) [@Nattawat](https://forum.cursor.com/u/Nattawat)\
**Post date:** [June 14, 2026, 1:30am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/57 "2026-06-14T01:30:38Z")

</div>

### Feature request for product/service

Chat

### Describe the request

First, thank you to the Cursor team. I use Cursor AI every day for real work (building our company platform), and it has helped me ship features I could not have done alone. I really appreciate the product.

**Feature request:** Add **Read aloud** (text-to-speech) to the chat message **“…”** menu (next to Copy).

**Why it would help**  
When a reply finishes, I often want to _listen_ while my hands are on other tasks. Today I can **Copy** from “…”, but there is no **Read** option.

**Current pain points**

1. Drag-select in the chat webview often misses nested list numbers and sub-bullets (they seem to live in separate DOM nodes). Main headings copy OK; nested bullets often do not.
2. I built a workaround with an external TTS script (Copy → listen), but native **Read aloud** on the same menu would be much easier and more reliable.

**Suggested UX**

- “…” menu: **Copy** | **Read aloud** | **Stop reading**
- Read the same full text as Copy (not partial selection)
- Optional: language / voice / speed (Thai support would be great for my team)

**Environment:** Windows 11 · Chat sidebar

Thank you again for Cursor — this small accessibility feature would make long AI replies much more useful for daily work.

### Screenshot / Screen Recording

 ![messageImage_1781400607356.jpg](https://us1.discourse-cdn.com/cursor1/original/3X/d/4/d46304425540637fc3c2100582062d3514240323.jpeg)

---

<div class="post-metadata">

**Author:** ![Kristian\_T](https://avatars.discourse-cdn.com/v4/letter/k/6f9a4e/32.png) [@Kristian\_T](https://forum.cursor.com/u/Kristian_T)\
**Post date:** [July 14, 2026, 10:34am UTC](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000/61 "2026-07-14T10:34:45Z")

</div>

I’d like to add the following use case to consider as a part of thinking of how to integrate voice related features into Cursor, I originally posted this in a separate idea thread - but merging my idea here as a reply to this one which already has traction:

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 initiatives. 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 for speech - such as summarising some of the key aspects of the table data - 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.

[Previous page](https://forum.cursor.com/t/text-to-speech-feature-request-for-reading-out-generated-code-and-explanations/23000.md?page=2)
