Audio Nodes

The Audio node generates sound from text. Use it to create voiceovers for your videos, background music for a scene, or sound effects that match a visual. Connect the output to a Video node to sync generated audio to a generated clip.

What you can generate

Speech / Voiceover — convert text to a natural-sounding voice narration.
Sound effects (SFX) — describe a sound and the model generates it.
Music — describe a musical mood, genre, or style to generate a short track.

How to use it:

  1. Add an Audio node to the canvas

  2. Select the type of audio you want: Speech, SFX, or Music

  3. Write a prompt or paste the text you want converted

  4. Choose a model and any available voice or style settings

  5. Click Generate

The audio plays back directly in the node. Connect the output to a Video node to use it as the soundtrack.

Connecting audio to video

The Audio node's output handle connects directly to a Video node's audio input. This lets you sync generated speech, music, or SFX to any video clip in your workflow.

For example: generate a product voiceover with the Audio node → connect it to a Video node showing your product → the final clip plays with the narration.

You can also use audio generation without a video — download the audio file directly from the node for use outside Berrys.