Turn text into audio directly inside your workflow
The Generate Audio node lets you convert text into spoken audio within Fluidfit. Provide a script, choose voice settings, and generate audio that you can preview or download for use in your workflows.
Add a Text node and enter your audio script
Connect the Text node to the Generate Audio node
Select voice, tone, and language options
Run the node
Audio is generated automatically
You can customize how your audio sounds:
Multiple voices
Different tones/styles
Multiple languages
Voice-specific variations
These options help you match the audio to your use case—formal, conversational, energetic, etc.
The Generate Audio node produces an Audio output:
Play audio directly in the browser ▶️
Download audio file for further use ⬇️
Use in downstream workflow nodes
View metadata (duration, format, bitrate, etc.)
Use dynamic text for automated narration
Try different voices to match your content tone