Audio model · from 8 credits
Generate a voice-over with Demucs
Demucs, Meta's open-source separator, splits a track into four stems: vocals, drums, bass and the rest of the instruments. It is the tool for remixes, karaoke and edits that need an isolated stem, and it works fast. Each stem comes back as a separate file, ready to download or wire back into the canvas.
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 Demucs for free?
Yes: signing up grants trial credits, no credit card required, and those credits never expire. Enough to test Demucs in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use Demucs?
No: Demucs 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 Demucs 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