Skip to main content
MindStudio
Pricing
BlogAbout
Log inGet Started
My Workspace
Text to Speech Model

Grok Voice TTS

Text to Speech by X.ai

Start Building with Grok Voice TTSView All Models
PublisherX.ai
TypeText to Speech
Context Window60,000 tokens
Released2026
Price$15 / 1M characters
LOW LATENCY
Try Grok Voice TTS →

Ready to build with Grok Voice TTS?

Get Started Free
Resources

Documentation & links

Grok Voice TTS on X.aiOfficial page
→
Official Website
→
Configuration

Parameters & options

VoiceSelect

Built-in voice, or paste a custom voice ID from the xAI console.

Default: eve
EveAltairAraAtlasAuroraCarinaCastorCelesteCosmoHeliosHelixIrisKeplerLeoLioraLumenLunaLuxNakshOrionPerseusRexRigelSalSiriusUrsaZaganZenith
LanguageSelect

BCP-47 language for synthesis. Auto detects from the text.

Default: auto
AutoEnglishArabic (Egypt)Arabic (Saudi Arabia)Arabic (UAE)BengaliChineseFrenchGermanHindiIndonesianItalianJapaneseKoreanPortuguese (Brazil)Portuguese (Portugal)RussianSpanish (Mexico)Spanish (Spain)TurkishVietnamese
SpeedNumber

Speech speed. 1.0 is normal. Range 0.7–1.5.

Default: 1Range: 0.7–1.5 (step 0.05)
Output FormatSelect
Default: mp3
MP3WAV
Normalize TextToggle Group

Spell out numbers, dates and abbreviations the way they are said.

Default: false
OnOff
Related models

Explore similar models

X.ai

Grok Voice 3.0

$0.08 / min of conversation
X.ai

Grok Voice (Think Fast 2.0)

$0.08 / min of conversation
X.ai

Grok Imagine 1.5 Lite

$0.02-$0.14/second
131.1K
Cartesia

Cartesia Sonic 3.6

~$37 / 1M characters
5K
Inworld

Inworld TTS-2

$35 / 1M characters
2K
ElevenLabs

ElevenLabs TTS

ElevenLabs TTS is a text-to-speech model from ElevenLabs that converts text into natural-sounding audio speech.

$0.04-$0.08 / 1k characters
10K

Start building with Grok Voice TTS

No API keys required. Create AI-powered workflows with Grok Voice TTS in minutes — free.

Get Started FreeExplore All Models