> For the complete documentation index, see [llms.txt](https://botsquare.gitbook.io/botsquare/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://botsquare.gitbook.io/botsquare/developer-guide/components/modal-conversion.md).

# Modal Conversion

We support the following modal conversion:

* [**Text to Audio**](#text-to-audio): convert text input to audio output.
* [**Audio to Text**](#audio-to-text): convert audio input to text output.
* [**Image to text**](#image-to-text): convert any *text in image* to text output. 

## Text to Audio

This component is used to generated a voice output based on any text. You can choose the type of voice you like.

![](https://4112697954-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FWlALaQ4M4Jr8FQTSwv7h%2Fuploads%2FGVVtWrKYpLZPdpXzEhF4%2FScreen%20Shot%202023-08-07%20at%203.38.39%20PM.png?alt=media\&token=c17e9095-e7ae-4116-86ee-93a79b4bfe45)

## Audio to Text

This component is used to generated a text output based on the user input audio. 

![](https://4112697954-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FWlALaQ4M4Jr8FQTSwv7h%2Fuploads%2FDekEjwlDbDaR65oQMRCg%2FScreen%20Shot%202023-08-07%20at%203.59.00%20PM.png?alt=media\&token=216c8268-f308-44c7-9cee-f865a79d2393)

## Image to Text

This module converts the text in an image to text format. The input should be an image, and the output will be a text string. 

![](https://4112697954-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FWlALaQ4M4Jr8FQTSwv7h%2Fuploads%2FvIq4Pch5kKLEHxcWJ0fO%2FScreen%20Shot%202023-08-07%20at%204.06.47%20PM.png?alt=media\&token=73e11d70-20be-4b29-80c1-fd6323fab179)