Audio model · from 2 credits
Generate a voice-over with MAI-Voice 2.1
MAI-Voice 2.1 is Microsoft AI's top voice model, released on October 1, 2026. It reads text in 23 languages with detailed prosody and a voice that holds steady from start to finish of a long text. Imaginode offers 33 of its voices, two to four per language, four of them French. It is the pick for a documentary voice-over, an audiobook or a training video. Speed is adjustable.
MAI-Voice 2.1 next to its closest siblings
Figures pulled from the same registry as billing: when a price or a cap changes, this table changes with it.
| MAI-Voice 2.1 | Fish Audio S1 | Fish Audio S2 Pro | |
|---|---|---|---|
| Base price | 4 credits / 1,000 characters | 3 credits / 1,000 characters | 3 credits / 1,000 characters |
| Voices | 33 | – | – |
| Max prompt | 6,000 characters | – | – |
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
How much does a voice-over generated with MAI-Voice 2.1 cost?
4 credits per 1,000 characters, about $0.05 (1 credit = $0.012). The exact cost shows before generating, and the MP3 downloads straight from the node.
Which voices does MAI-Voice 2.1 offer?
33 to choose from, with adjustable playback speed, up to 6,000 characters per generation. The voice-over node produces a downloadable MP3, billed per character.
Can I try MAI-Voice 2.1 for free?
Yes: signing up grants trial credits, no credit card required. Enough to test MAI-Voice 2.1 in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use MAI-Voice 2.1?
No: MAI-Voice 2.1 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 MAI-Voice 2.1 on a real canvas
121 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
ElevenLabs v3
MiniMax Speech 2.8 HD