---
title: "Turn text into speech"
description: "Listen to a Bearly answer or create downloadable spoken audio with the voice and delivery you want."
canonical: "https://bearly.ai/docs/features/text-to-speech/"
markdown: "https://bearly.ai/docs/features/text-to-speech.md"
---

# Turn text into speech

HTML: [https://bearly.ai/docs/features/text-to-speech/](https://bearly.ai/docs/features/text-to-speech/)

> Listen to a Bearly answer or create downloadable spoken audio with the voice and delivery you want.

Bearly can read an answer aloud or turn text into an audio file. Use **Read aloud** when you simply want to listen. Use **Text to Speech** when you want a downloadable recording or need to direct the voice, pace, tone, accent, or emotion.

## Listen to an answer

After Bearly returns a text answer, select **Read aloud** beneath it. Select the same control again to stop playback.

This is the quickest way to listen while proofreading, reviewing a long response, or working away from the screen. If playback does not begin, check that the device is not muted and that the browser or operating system allows audio from Bearly.

## Create an audio file



1. **Choose Text to Speech**

   In a chat, type `/tts`, then select **Text to Speech** from the command menu.

2. **Add the words and direction**

   Paste or type the text you want spoken. If the delivery matters, describe it plainly in the same message.

   ```text copy
   Read this in a measured, warm voice. Pause slightly between the two paragraphs and keep the ending understated:

   [Paste the text here]
   ```

3. **Send the message**

   Bearly creates an audio player in the conversation. Play the recording there, or use its download control to save an MP3.



The generated audio remains with the chat, which makes it easy to compare versions. To change the performance, send the text again with more specific direction—for example, “slower,” “less formal,” or “with a quiet, reassuring delivery.”

> **Tip — Direct the performance, not the technology**
> Describe how the result should sound to a listener. A short note about pace, mood, emphasis, or accent is usually more useful than a long technical specification.


## If the audio is not right

- If a name or unusual term is mispronounced, spell it phonetically in the text and generate another version.
- If the delivery feels exaggerated, simplify the direction to one or two qualities.
- If generation fails, shorten a very long passage and try again after checking the connection.
- If an older recording says it is no longer available, generate it again from the original text. Download important finished recordings rather than relying on an old chat as permanent audio storage.

## Continue through the documentation

- [Documentation index](https://bearly.ai/docs.md): Browse every Bearly guide.
- [Previous: Transcribe audio and video](https://bearly.ai/docs/features/transcripts.md)
- [Next: Use your computer with Bearly](https://bearly.ai/docs/features/computer-use.md)