> ## Documentation Index
> Fetch the complete documentation index at: https://docs.packagesss.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Audio

> Convert text to speech using AI

The AI Audio node uses the AI to convert text to speech. This is useful for creating audio files from text.

It uses ElevenLabs under the hood.

## Common options

<Note>
  Learn what [Bypass Node](/common/bypass-node), [JSON Keys](/common/json-keys), [Taggable Steps](/common/taggable-steps), and [Match Up Steps](/common/match-up-steps) do.
</Note>

## Inputs

### Modes

These are the modes that you can choose from:

<Steps>
  <Step title="Text to Speech">
    Converts text to speech using AI via ElevenLabs
  </Step>

  <Step title="Sound Effect">
    Converts text to sound effect using AI via Elevenlabs
  </Step>
</Steps>

#### Text to Speech

Here are the settings that you can use to customize your text to speech audio:

<Steps>
  <Step title="Text to Speech Script">
    The actual text that will get spoken by the AI.
  </Step>

  <Step title="Voice to use">
    The voice to use when speaking the text.
  </Step>
</Steps>

#### Sound Effect

<Steps>
  <Step title="Describe the sound effect">
    The description of the sound effect you want to generate.
  </Step>
</Steps>

## Output

The output of this node is a URL to the audio file that was generated.

Here's an example.

```
https://milkylabs.s3.amazonaws.com/f-af400b06-101b-46db-864b-ab86ac27ddcc-Ztl0RB-1744552978537.mp3
```

## Video Walkthrough

Below is a video walkthrough of how to use the AI Audio node.

<iframe width="560" height="315" src="https://www.youtube.com/embed/_UE5PiQrH80?si=Is-fqTrVba6W9J7K" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen />
