# Speech-to-Text Functionality Issues with Image Pasting in Agent Mode

**URL:** <https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003>\
**Category:** Feature Requests\
**Tags:** voice\
**Created:** [May 31, 2026, 1:50am UTC](https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003 "2026-05-31T01:50:22Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ilan\_Aviv](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/ilan_aviv/32/110173_2.png) [@Ilan\_Aviv](https://forum.cursor.com/u/Ilan_Aviv)\
**Post date:** [May 31, 2026, 1:50am UTC](https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003/1 "2026-05-31T01:50:22Z")

</div>

**Problem Summary:**

Currently, there are two issues limiting the flexibility of speech-to-text in the Agent typing bar:

1. **Speech-to-Text Disabled After Image Paste**

2. **Cannot Continue Speech Input**

**Impact:**

Many users rely on speech-to-text as their primary method for prompt injection while working with Agents. These limitations reduce workflow efficiency and flexibility.

**Feature Request:**

Enable speech-to-text to work seamlessly alongside image pasting and allow multiple consecutive speech-to-text inputs without interruption.

---

<div class="post-metadata">

**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\
**Post date:** [June 1, 2026, 1:05pm UTC](https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003/6 "2026-06-01T13:05:38Z")

</div>

Hey @Ilan_Aviv!

Thanks for the report!

I believe that both of these issues have been solved over in the Agent Window (the Editor Window may be lagging behind). Could you confirm you’re facing these issues in the Editor window?

---

<div class="post-metadata">

**Author:** ![Ilan\_Aviv](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/ilan_aviv/32/110173_2.png) [@Ilan\_Aviv](https://forum.cursor.com/u/Ilan_Aviv)\
**Post date:** [June 2, 2026, 3:04am UTC](https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003/9 "2026-06-02T03:04:00Z")

</div>

![image](https://us1.discourse-cdn.com/cursor1/original/3X/e/e/eee573debef40b65bbdb16bc3b6733b8c8b11911.png)  
New to Cursor - looks like the agent window in app. Attaching a screenshot that might explain the issue much better. A part of attaching files that disable the microphone speech to text, also - whenever stopping the speech to text, It’s not possible to keep on. As you can see in the screenshot.

It looks to me that whenever some text injected into the typing area It disable the microphone.

---

<div class="post-metadata">

**Author:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\
**Post date:** [June 2, 2026, 12:02pm UTC](https://forum.cursor.com/t/speech-to-text-functionality-issues-with-image-pasting-in-agent-mode/162003/10 "2026-06-02T12:02:10Z")

</div>

That’s the Editor Window! So it falls into the existing issue we know about.

In the event that the Agents Window suits your needs, you’ll find that both issues are solved there (you can always continue speech-to-text, even if you’ve pasted an image or started/stopped a recording)

 ![Screenshot 2026-06-02 at 13.59.52](https://us1.discourse-cdn.com/cursor1/original/3X/2/0/2081c5735c8738c29b0cea5fd8d63d15da715f18.png)