# vision image to text

**URL:** <https://forum.rabbitcommunity.tech/t/vision-image-to-text/13516>\
**Category:** all things rabbit\
**Created:** [August 18, 2024, 7:08pm UTC](https://forum.rabbitcommunity.tech/t/vision-image-to-text/13516 "2024-08-18T19:08:50Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![ramses](https://sea2.discourse-cdn.com/flex002/user_avatar/forum.rabbitcommunity.tech/ramses/32/4315_2.png) [@ramses](https://forum.rabbitcommunity.tech/u/ramses)\
**Post date:** [August 18, 2024, 7:08pm UTC](https://forum.rabbitcommunity.tech/t/vision-image-to-text/13516/1 "2024-08-18T19:08:50Z")

</div>

is it currently possible with r1 to capture an image and transcribe it to text?

---

<div class="post-metadata">

**Author:** ![BlueNexus9](https://sea2.discourse-cdn.com/flex002/user_avatar/forum.rabbitcommunity.tech/bluenexus9/32/3692_2.png) [@BlueNexus9](https://forum.rabbitcommunity.tech/u/BlueNexus9)\
**Post date:** [August 18, 2024, 7:17pm UTC](https://forum.rabbitcommunity.tech/t/vision-image-to-text/13516/2 "2024-08-18T19:17:29Z")

</div>

Hi @ramses ,  
do you mean a description of the picture?

The description can be shown in the rabbit-hole.

An other possible way could be the ‘beta rabbit’ in the vision mode. After the vision mode, maybe you can save the result of the vision mode in a note.

---

<div class="post-metadata">

**Author:** ![ramses](https://sea2.discourse-cdn.com/flex002/user_avatar/forum.rabbitcommunity.tech/ramses/32/4315_2.png) [@ramses](https://forum.rabbitcommunity.tech/u/ramses)\
**Post date:** [August 18, 2024, 7:19pm UTC](https://forum.rabbitcommunity.tech/t/vision-image-to-text/13516/3 "2024-08-18T19:19:48Z")

</div>

_og rabbit_ would always just summarize what’s on the original doc – beta rabbit transcribed it properly.

thanks a lot @BlueNexus9 〜