# Text to Speech

{% hint style="info" %} <mark style="color:red;">**Location: Activities**</mark> <mark style="color:red;"></mark><mark style="color:red;">→</mark> <mark style="color:red;"></mark><mark style="color:red;">**Text to Speech**</mark>
{% endhint %}

This page displays a log of all **Text-to-Speech (TTS)** conversions performed from your account. Each entry provides detailed information about the audio file generated from a text input.

**Displayed Fields:**

<figure><img src="https://1128185770-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LYT_KLa68bpbaUhamSb%2Fuploads%2Fgj0iQYXaKMR3Xr9VB5OY%2Fimage.png?alt=media&#x26;token=d900e647-723e-45bd-b7a7-827aecd22a60" alt=""><figcaption></figcaption></figure>

| Field                  | Description                                                                                                               |
| ---------------------- | ------------------------------------------------------------------------------------------------------------------------- |
| **Engine**             | The TTS engine used for conversion (Neural/Standard).                                                                     |
| **Language**           | Language code or name selected for speech synthesis (e.g., `en-US`).                                                      |
| **Voice ID**           | The specific voice selected for speech output (e.g., `Joanna`, `Matthew`).                                                |
| **Volume**             | Volume level used during synthesis (e.g. Default).                                                                        |
| **Rate**               | Speaking rate of the voice (e.g., `slow`, `medium`, `fast`, or percentage adjustment).                                    |
| **Pitch**              | Pitch setting used to alter the voice’s tone (e.g., `low`, `medium`, `high`).                                             |
| **Record Text**        | The actual text content that was converted to speech.                                                                     |
| **Record Text Length** | Number of characters or words in the record text, depending on system design.                                             |
| **Cost**               | Cost incurred for generating the speech file, based on engine pricing and text length.                                    |
| **File**               | Option to play and listen to the audio file.                                                                              |
| **Created At**         | Timestamp indicating when the TTS conversion was created.                                                                 |
| **Action**             | Available actions such as download(Download button to the generated audio file) and add this file to the recording module |

If no data is available, the message **"No matching records found"** will be displayed.