Audio model · from 2 credits
Generate a voice-over with Grok TTS
Grok TTS is xAI's synthetic voice, billed per character at a tiny rate. It produces a clear, modern read, suited to short-video voice-overs, script tests and audio mock-ups. In the canvas you write the text, pick the voice, and the track comes out ready to lay on an edit. For projects where the voice carries the piece, Fish Audio and OpenAI TTS HD offer other timbres to compare on the same sentence.
Five voices, billed per character
Grok TTS is xAI's speech engine. It offers five voices, Eve, Ara, Rex, Sal and Leo, in a clear modern register that suits short-form voice-over, sound mock-ups and script tests. The read is clean, without the mispronunciations that gave away the engines of two years ago.
Its rate is counted per character and it is tiny: reading a whole script costs less than one image. That makes it the right tool for trying, rewriting and retrying a line until it sounds right, before handing it to a premium engine if the project warrants one.
Directing the read with tags
xAI offers no tone setting: performance direction goes through tags written inside the text itself. The canvas gives them in one click, [pause], [laugh], [whisper], [excited], [sigh], and they go exactly where a performer would breathe, smile or drop their voice.
Well placed, those tags change everything: a pause before the end of a sentence beats a pile of adjectives in the instruction. Badly placed, they chop the read up. The working method is to set one or two, listen, then adjust, rather than scattering them everywhere on the first pass.
Where it stops, and what replaces it
Grok TTS reads well, but it does not act. For a project where the voice is the heart of the result, a character that must move someone, a long narration, a dub, the catalogue's specialised engines offer other timbres and finer direction. Cloning an existing voice needs an engine that says so explicitly.
On the canvas the track comes out of the Voice node ready to sit on an edit: it wires into a Montage node with the video clips, or into a Video node that accepts a reference voice. Comparing two engines on the same text takes two nodes and one click.
Grok TTS 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.
| Grok TTS | Fish Audio S1 | Fish Audio S2 Pro | |
|---|---|---|---|
| Base price | 3 credits / 1,000 characters | 3 credits / 1,000 characters | 3 credits / 1,000 characters |
| Voices | 5 | – | – |
| Max prompt | 15,000 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 many voices does Grok TTS offer?
Five, named Eve, Ara, Rex, Sal and Leo. They are picked in the Voice node, and the same line can be generated by several of them to compare before deciding.
Can I set emotion or pacing?
Not through a setting: xAI works through tags written in the text, such as [pause], [whisper] or [excited]. The canvas offers them in one click, to place where the read should change.
Can Grok TTS clone my own voice?
No, it reads with its five voices. Cloning needs an engine that announces it explicitly: the catalogue has some, with their own terms and their own rate.
How much does a voice-over generated with Grok TTS cost?
3 credits per 1,000 characters, about $0.04 (1 credit = $0.012). The exact cost shows before generating, and the MP3 downloads straight from the node.
Which voices does Grok TTS offer?
5 to choose from, with adjustable playback speed, up to 15,000 characters per generation. The voice-over node produces a downloadable MP3, billed per character.
Can I try Grok TTS for free?
Yes: signing up grants trial credits, no credit card required. Enough to test Grok TTS in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use Grok TTS?
No: Grok TTS 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.
Grok TTS at the competition
Grok TTS or its variants are also available at ElevenLabs. Pricing grid recorded on a given date, sources cited: the comparison details what credit-based billing changes.
Read the Imaginode vs ElevenLabs comparison →
Try Grok TTS on a real canvas
116 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
ElevenLabs v3
MiniMax Speech 2.8 HD