Audio model · from 11 credits
Generate a voice-over with DeepFilterNet 3
DeepFilterNet 3 is the voice cleaner of the Enhance mode. It strips background noise from a spoken recording, hiss, hum, keyboard, and upsamples the audio to 48 kHz along the way. It is the gentle treatment: the voice keeps its grain and a little of the room's air, which makes it ideal for rescuing an average mic take without denaturing it. For a truly invasive background, music included, ElevenLabs isolation makes the radical move.
Capabilities
- Durations: 1–600 s
How to use it on Imaginode
- 1Add a Voice-over node from the toolbar.
- 2Write or wire in the text to read, pick a voice: the price follows the text length.
- 3Generate, listen in the node and download the MP3.
Frequently asked questions
Can I try DeepFilterNet 3 for free?
Yes: signing up grants trial credits, no credit card required, and those credits never expire. Enough to test DeepFilterNet 3 in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use DeepFilterNet 3?
No: DeepFilterNet 3 runs server-side, in the browser, mobile included. Imaginode's node canvas wires its renders to the other models (references, camera, styles) with nothing to install.
Try DeepFilterNet 3 on a real canvas
49 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
ElevenLabs v3
MiniMax Speech 2.8 HD