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

# Generate Audio

Audio Nodes in ImagineArt Workflows enable you to generate professional spoken voice, original music, and custom sound effects entirely from text. Whether you need a voiceover for video, a background track, or sound effects for animation, these AI-powered nodes produce broadcast-quality audio that integrates seamlessly into your creative pipeline.

## How to Add Audio Nodes

1. Click the Add (+) button on the left toolbar in the workflow canvas.
2. Select Audio under node categories.
3. Choose from the available nodes listed below.

You can also double-click anywhere on the canvas and search for any audio node by name.

## Generation Nodes

These nodes create audio content from text prompts.

<Steps>
  <Step title="Generate Audio">
    Convert text into natural-sounding speech. Write what you want spoken, select a voice character, and generate realistic audio. Supports multiple voices and models including ElevenLabs TTS and Minimax 2.8 HD.
  </Step>

  <Step title="Generate Music">
    Generate original music tracks from text descriptions or lyrics. Describe the mood, genre, and instruments or write full lyrics and the AI composes a complete track. Powered by ElevenLabs Music.
  </Step>

  <Step title="Sound Effects">
    Generate custom sound effects from text descriptions. Describe any sound like rain, footsteps, explosions, sci-fi ambiance and the AI creates a matching audio clip. Powered by ElevenLabs Sound Effects.
  </Step>
</Steps>

## Combining Nodes

Audio nodes are designed to feed into the rest of your workflow. Here are some common combinations:

* **Voice → Combine Audio & Video**: Generate a voiceover and layer it onto an AI-generated video.
* **Music → Combine Audio & Video**: Create a custom soundtrack and pair it with a product video or brand reel.
* **Sound Effects → Combine Audio & Video**: Add ambient sounds or action effects to animated scenes.
* **Voice → Lipsync**: Generate speech, then use it as the audio input for a Lipsync node to create a talking-head video.
* **Text Iterator → Voice**: Enter multiple scripts and generate a separate voiceover for each — perfect for multilingual content or personalized outreach.
* **Prompt → Music + Prompt → Generate Video → Combine Audio & Video**: Create both a video and its soundtrack from text, then merge them into a finished piece.