# Enhancement Suggestion: Live Text Display in Voice Mode for Better UX

**URL:** <https://community.openai.com/t/enhancement-suggestion-live-text-display-in-voice-mode-for-better-ux/1122982>\
**Category:** Feature requests\
**Tags:** advanced-voice\
**Created:** [February 17, 2025, 4:53pm UTC](https://community.openai.com/t/enhancement-suggestion-live-text-display-in-voice-mode-for-better-ux/1122982 "2025-02-17T16:53:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tiagocarvalho](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/tiagocarvalho/32/553711_2.png) [@tiagocarvalho](https://community.openai.com/u/tiagocarvalho)\
**Post date:** [February 17, 2025, 4:53pm UTC](https://community.openai.com/t/enhancement-suggestion-live-text-display-in-voice-mode-for-better-ux/1122982/1 "2025-02-17T16:53:31Z")

</div>

**Hey OpenAI Team and Community,**

First of all, huge congratulations on the incredible progress with ChatGPT! The voice mode is truly impressive, making interactions feel more natural and engaging. However, after using it extensively, I noticed an area that could **greatly enhance the user experience**.

### **Current Limitation in Voice Mode**

At the moment, when ChatGPT is in voice mode, **users do not see the text of the AI’s response while it is being spoken**. This makes it difficult to:  
✅ Follow longer or more complex responses.  
✅ Comprehend information clearly in noisy environments.  
✅ Retain key points without replaying the response.  
✅ Skim through or reference the response after the interaction ends.

### **Proposed Improvement: Live Text Display**

To address this, I suggest modifying the **UI for voice interactions** to provide a more intuitive and accessible experience:

1️⃣ **Minimized UI** – Instead of keeping the ChatGPT interface fully visible, shrink it to a **small indicator in the corner** that shows when the AI is **listening, processing, or speaking**.  
2️⃣ **Live Text Display** – While ChatGPT is speaking, **display the response as text in real-time**. This would allow users to **read along, skim, and better absorb information** without needing to rely solely on audio.  
3️⃣ **Toggle Option for Flexibility** – Some users might prefer to keep the current experience, so having a **toggle in settings** to enable or disable live text display would ensure flexibility for different preferences.

### **Why This Would Be a Game-Changer**

🎯 **Improved Comprehension** – Seeing the text while hearing the response helps with clarity and retention.  
🎯 **Accessibility & Inclusivity** – Beneficial for users with hearing difficulties or those who process information better visually.  
🎯 **Enhanced Multi-Modal Experience** – A seamless combination of **text and speech** makes interactions smoother.  
🎯 **More User Control** – Allows users to scan responses without needing to replay audio.

### **Community Thoughts?**

Would love to hear what others think! If you also feel this would improve voice mode, let’s give it visibility so OpenAI can prioritize it. If anyone has **additional ideas to refine this concept** , feel free to share!

**OpenAI Team:** If this aligns with your roadmap, I’d be happy to test it in beta or provide further feedback. Thanks for considering! 🙌