Grok TTS is the text-to-speech model from xAI's Grok Voice family, listed on fal as xAI Text to Speech. You give it text and a voice, and it returns spoken audio. Every generation is saved to My Creations.

Can I hear the voices before I generate?

Yes. The play button next to the voice picker plays a short sample of the selected voice. Previews are free.

Which languages are supported?

Twenty: English, Chinese, Japanese, Korean, French, German, Italian, Spanish (Spain and Mexico), Portuguese (Brazil and Portugal), Russian, Turkish, Vietnamese, Indonesian, Hindi, Bengali, and Arabic (Egypt, Saudi Arabia and UAE). You can also leave it on auto-detect.

How do the expression tags work?

Put [laugh], [pause] or [sigh] where you want it to happen. To change how a phrase is spoken, wrap it: like this or like this . The buttons under the text box insert them for you.

How long can the text be?

Up to 15,000 characters per generation. For anything longer, split it into parts and generate each one.

How many credits does it cost?

3 credits per 1,000 characters, rounded up, with a minimum of 1 credit per generation. A typical 200-character line costs 1 credit. Expression tags count toward the length. Text is measured in UTF-8 bytes, so each character in scripts such as Chinese or Japanese counts as up to three.

Can I use the audio for a talking photo?

Yes. Download the MP3, then upload it on the Lip Sync page with a portrait photo. Lip sync needs at least 5 seconds of audio and uses up to the first 14.8 seconds.

AI Text to Speech

Turn text into natural-sounding speech with Grok TTS. 28 voices, 20 languages, and inline tags for laughs, pauses and whispers.

Grok TTS

Text0 / 15,000

Expression tags:

Voice

28 voices. Press play to hear a short sample before you generate.

Language

Cost: 1 credit

Sample voices

EveNarration

“Welcome back. Today we're walking through three habits that quietly changed how I work, and the first one takes less than a minute.”

LeoAd read

“Tired of recording the same voiceover ten times? [laugh] Same. Type it once, pick a voice, and you're done.”

AuroraStorytelling

“The house was quiet. <whisper>Too quiet.</whisper> [pause] And then, somewhere upstairs, a door clicked shut.”

What Grok TTS can do

A text-to-speech model from xAI, with expressive delivery written straight into the text.

28 voices, each with a preview

Every voice has a short sample you can play before you spend a credit, so you are not choosing from names alone.

20 languages, or auto-detect

English, Chinese, Japanese, Korean, Spanish, French, German, Arabic and more. Leave it on auto-detect and the model reads the language from your text.

Laughs, pauses and whispers in the script

Drop [laugh], [pause] or [sigh] into the text, or wrap words in whisper or slow tags. The sample voices on this page use them.

Up to 15,000 characters

Enough for a full script in one go. You get an MP3 at 24 kHz and 128 kbps to download or drop into a video.

How to turn text into speech

Three steps, no recording needed.

Write or paste your script

Up to 15,000 characters. Add expression tags where you want a laugh, a pause or a whisper.

Pick a voice and language

Preview any of the 28 voices first. Leave the language on auto-detect unless your text mixes languages.

Generate and download

Your audio appears next to the editor and in My Creations. Download it as an MP3.

Frequently asked questions

What the text-to-speech tool does, what it costs, and how it fits with the rest of Veevid.

Give your script a voice

Pick one of 28 voices, add a laugh or a pause where it fits, and download the MP3.

Start generating