popnow
Sign inStart creating

by xAIAudio

Grok TTS

71 voices across 20 languages with speech tags

  • 71 voices
  • 20 languages
Try Grok TTS

From 3 credits per 1,000 characters≈ $0.03

What it's like to use

Grok TTS from xAI reads up to 15,000 characters per request in 71 preset voices across 20 languages. Laughs, breaths, pauses and whispers go straight into the script as tags, and a speed slider slows things down for a bedtime read.

Good for

  • Audiobook chapters with one consistent narrator
  • Multilingual narration from one script
  • Phone menus in formats a phone system can play directly

What Grok TTS can do

Each mode opens in the studio with Grok TTS already picked. The price shows before you generate.

Text to SpeechTurn a script into natural speech in hundreds of voices.From 3 creditsper 1,000 characters

How to prompt Grok TTS

  1. Add sounds where they happen with tags like [pause], [laugh] or [breath].
  2. Wrap words in <whisper>…</whisper> or <slow>…</slow> to change how that passage is read.
  3. Pick a voice made for the script's language, or use one of the five voices that speak every supported language.

Settings worth knowing

Everything else has a sensible default, so you can type a prompt and go.

voice_id71
Pick from the available voices.
language20
The language of the speech.
speed0.7–1.5
Speaking pace.
output_formatmp3 · wav · pcm · mulaw · alaw
File type of the result.

How it compares

Same kind of job, different strengths and prices.

Gemini 3.8 Flash TTS gives a more acted read with two voices in one file. Grok is the one for long scripts in one request.

Grok TTSThis modelFrom 3 credits
Gemini 3.8 Flash TTSExpressive speech that acts out cues like [laughing]From 0.05 creditsper second of audioMiniMax Speech 2.8 HDHigh-fidelity speech in 400+ voices with emotion controlFrom 18 creditsper 1,000 charactersGemini 3.8 Flash-Lite TTSFast, lightweight speech in 30 voicesFrom 0.03 creditsper second of audioSeed Speech 2.041 voices with tone set in plain languageFrom 11 creditsper 1,000 charactersMiniMax Speech 2.8 TurboFast speech in 400+ voices with emotion controlFrom 11 creditsper 1,000 charactersQwen3 TTSOpen-source speech with tone and pace set in plain wordsFrom 11 creditsper 1,000 characters

Questions about Grok TTS

How much does Grok TTS cost?

On PopNow, the cheapest run of Grok TTS costs 3 credits ($0.03) per 1,000 characters. You pay with credits (1 credit = $0.01), the exact cost shows on the Generate button before you start, and failed generations are refunded automatically.

What can Grok TTS do?

On PopNow, Grok TTS works in these modes: Text to Speech. Pick one in the studio and add a prompt or an upload.

How should I write prompts for Grok TTS?

Add sounds where they happen with tags like [pause], [laugh] or [breath]. Wrap words in <whisper>…</whisper> or <slow>…</slow> to change how that passage is read. Pick a voice made for the script's language, or use one of the five voices that speak every supported language.

Grok TTS or Gemini 3.8 Flash TTS?

Gemini 3.8 Flash TTS gives a more acted read with two voices in one file. Grok is the one for long scripts in one request.

Do I need to install anything to use Grok TTS?

No. Grok TTS runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.

Building an app? See the Grok TTS API →

Make something with Grok TTS

Type an idea, pick your settings and see the price before you hit Generate.

Try Grok TTS All models