Audio Nodes

Audio Nodes allow you to incorporate audio context into your AI generations. You can use them to provide spoken instructions, transcripts, or any audio reference that a Text Node can analyze.

Creating an Audio Node

To create an Audio Node, right-click on the canvas and select Audio Node from the context menu.

Input Methods

The Audio Node supports two ways to provide audio:

1. Upload Audio

You can upload an existing audio file from your computer.

• Click the Upload Audio button.
• Select a supported audio file (e.g., MP3, WAV, WEBM).
• The audio will be uploaded and visualized with a waveform.

2. Record Microphone

You can record audio directly from your browser.

• Click the Record Mic button.
• Grant microphone permissions if prompted.
• Speak your instruction or content.
• Click Stop Recording when finished.
• The recording will be saved and ready to use.

Using Audio Nodes

Once you have an Audio Node with content:

1. Connect to Text Node: Drag a connection link from the Audio Node’s handle (right side) to a Text Node.
2. Generate: When you generate the Text Node, the AI will listen to the attached audio and use it as context for its response.

This is particularly useful for summarizing meetings, transcribing voice notes, or following spoken prompt instructions.