Audio generation
Available now

Grok TTS

by xAI

xAI's voice model for reads that perform.
Five voices, laughs on cue, words you can whisper.

Grok TTS

Key features

Technical specifications

5

Built-in voices, each speaking every supported language

15,000 chars

Maximum script length per generation on Morphic

Inline + wrap

Sound cues inline, delivery tags around words

MP3, 24 kHz

128 kbps audio, ready for a timeline

Use cases

Glass steps edged in cool light climbing into depth

Explainers and tutorials

Rex for a clear walkthrough, Sal for a calmer one. Regenerate a single step when the product changes.

A loud coral burst of light with one quiet silver trail drifting away

Ads and promos

Eve's energy for a launch read, with a whispered aside wrapped in a tag so only those words drop.

Five glowing beads each sending a ribbon of light in its own direction

Localized voice-over

Keep the same voice across markets. Paste each translation and the voice follows the language.

A winding river of amber light curving into darkness

Story and podcast narration

Long scripts in one pass, with pauses and laughs written where the beat lands.

A soft round glow of warm peach light

Assistant and app voices

Ara's warmth for onboarding, help and spoken notifications that should sound friendly.

A heavy shaft of white light striking down through haze

Announcements and trailers

Leo's weight for a trailer line or an announcement that needs to sound like it matters.

Prompt examples

A straight white line of light breaking into sparks at its centre

Laugh mid-line

I tried to fix it myself. [laugh] We now have two broken taps.

0:00
0:12
Edit prompt
A faint wisp of silver mist narrowing to a point

Whispered secret

Don't tell anyone, but <whisper>the surprise is on Friday</whisper>.

0:00
0:12
Edit prompt
Two bright points of light far apart with darkness between them

Dramatic pause

The results are in. [long-pause] We won.

0:00
0:12
Edit prompt
A teal ribbon of light slowing into wide loops

Slow emphasis

Read the label. Then <slow>read it again</slow> before you plug it in.

0:00
0:12
Edit prompt
A warm golden glow, soft and round, in mist

Spanish read

Bienvenidos. Hoy vamos a preparar el pan más fácil del mundo.

0:00
0:12
Edit prompt
A burst of coral, mint and yellow light points like confetti

Launch read

New season, new colours, and free returns on every order this week.

0:00
0:12
Edit prompt

Overview

Grok TTS is xAI's text-to-speech model, on Morphic since July 2026. It reads a script in one of five built-in voices, performs sounds like a laugh or a pause where you write them, and changes the delivery of any words you wrap in a tag.

What Grok TTS does differently

Grok gives you two kinds of direction inside the script. Sound cues sit inline in square brackets, so [laugh] happens at that point in the line. Delivery tags wrap words, so <whisper> changes only what sits between the opening and closing tag. The voices are few but not tied to a language: each of the five speaks every language Grok supports, which keeps one voice consistent from the English cut to every translation.

Grok TTS on Morphic

On Morphic, Grok TTS sits in the Audio model picker for Speech as xAI Grok TTS. Choose Eve, Ara, Rex, Sal or Leo, paste a script of up to 15,000 characters with any tags inline, and generate. Grok detects the language from the text, and the audio comes back as MP3 on your Canvas. For a larger voice library or cloned voices, ElevenLabs v4 runs in the same picker.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$19/ month
billed as $228 per year

2400 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $288 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $540 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Max

$170/ month
billed as $2040 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows

FAQs

What is Grok TTS?
Grok TTS is xAI's text-to-speech model. It reads a script in one of five built-in voices, performs sound cues like a laugh or a pause where you place them, and changes delivery on words you wrap in tags. On Morphic it has run in Speech since July 2026.
Which voices does Grok TTS have?
Five built-in voices: Eve (energetic and upbeat), Ara (warm and friendly), Rex (confident and clear), Sal (smooth and balanced) and Leo (authoritative and strong). Each one speaks every supported language, so the voice you cast for English can read the Spanish or Japanese version too.
How do I add a laugh or a pause?
Write the cue in square brackets where it should happen, such as [laugh], [pause] or [long-pause]. Grok performs the cue at that point instead of reading it out. Keep cues next to the words they belong to.
How do I whisper or slow down part of a line?
Wrap the words in a pair of tags, such as <whisper>this part</whisper> or <slow>this part</slow>. Only the wrapped words change. You can nest two tags, like a slow, soft phrase, but keep it to a few words so the rest of the line stays natural.
What languages does Grok TTS speak?
xAI lists the languages in its text-to-speech documentation, including English, Spanish, French, German, Portuguese, Arabic, Hindi, Japanese, Korean and Chinese. Grok detects the language from the script, so paste the text in the language you want to hear.
How long can a Grok TTS script be?
Up to 15,000 characters per generation on Morphic. That covers a long narration or a full podcast segment in one take, so there is less stitching between pieces.
How is Grok TTS different from ElevenLabs on Morphic?
Both produce expressive speech on Morphic. ElevenLabs gives you a large voice library, voice cloning and voice settings. Grok TTS keeps it simple: five voices that each speak every supported language, and tags for sounds and delivery written into the script. It suits teams that want one consistent voice across markets without casting.
Is Grok TTS free to use on Morphic?
Yes, Grok TTS runs on Morphic's free tier. Credits are charged by the length of the script, and paid plans add more credits for longer and more frequent reads.
How do I use Grok TTS on Morphic?
Open Morphic, switch the prompt bar to Audio and choose Speech. Pick xAI Grok TTS as the model, choose one of the five voices, paste your script with any tags, and generate. The audio lands on your Canvas alongside your video clips.