No filming:An AI avatar or clone yourself

    Grok · Audio model

    Grok TTS: specs, pricing and how to use it

    xAI Grok TTS - high-quality text-to-speech with 5 expressive voices, 21 languages, and speech tags support. Up to 15,000 characters per request.

    4 credits per 1,000 characters#29 overall

    One account for the web and iPhone.

    Grok TTS is xAI's text-to-speech model. You paste a script of up to 15,000 characters, choose a voice and a language (or leave the language on auto-detect), and it reads the script aloud. Inline tags such as [pause] or [laugh] add a sound at one point, and wrapping tags such as <whisper>...</whisper> change how a passage is delivered. On Versely it costs 4 credits per 1,000 characters.

    What Grok TTS is best at

    Text to audio
    Text to speechMulti languageExpressiveSpeech tags21 languages

    Pricing

    Grok TTS costs 4 credits per 1,000 characters on Versely. It bills per 1,000 characters of input text.

    OptionPrice
    per 1,000 characters4 credits

    Prices are Versely credits. Your plan's credit allowance is on the pricing page.

    Inputs

    Text prompt

    Generates from a written prompt - no media upload required.

    Rankings

    Grok TTS ranks #29 overall with an Elo score of 1157 on Versely's live model rankings.

    CategoryRankEloMeasured
    Text to audio#291157-

    Release

    Grok TTS was released on March 16, 2026 (released 8 months ago).

    Other audio models

    Use Grok TTS inside these tools

    Frequently asked questions

    How much does Grok TTS cost on Versely?+

    Grok TTS costs 4 credits per 1,000 characters on Versely.

    What is Grok TTS best for?+

    xAI Grok TTS - high-quality text-to-speech with 5 expressive voices, 21 languages, and speech tags support. Up to 15,000 characters per request. On Versely it is filed as a Grok audio model for text to audio.

    How does Grok TTS rank against other audio models?+

    Grok TTS ranks #29 overall with an Elo score of 1157 on Versely's live model rankings.

    Does Grok TTS need a voice sample?+

    No. Grok TTS generates audio from a text prompt alone.

    When was Grok TTS released?+

    Grok TTS was released on March 16, 2026 (released 8 months ago).

    What voices does Grok TTS have?+

    xAI's documentation lists built-in voices including Eve, its default, plus Ara, Leo, Rex and Sal, and says every built-in voice can speak every supported language. Voice and language are set separately, so one voice can read the English and the Hindi version of the same script.

    Which languages does Grok TTS support?+

    xAI lists 20: English, Arabic (Egypt, Saudi Arabia and the UAE), Bengali, Chinese (Simplified), French, German, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese (Brazil and Portugal), Russian, Spanish (Mexico and Spain), Turkish and Vietnamese. You can also leave the language on auto-detect.

    How do Grok TTS speech tags work?+

    There are two kinds. An inline tag in square brackets, such as [pause] or [laugh], makes a sound at the point where you type it; xAI groups these as pauses, laughter and crying, mouth sounds and breathing. A wrapping tag, such as <whisper>it was a secret</whisper>, changes how the words between the opening and closing tag are said; its groups are volume and intensity, pitch and speed, and vocal style such as singing.

    Try Grok TTS inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.

    One account for the web and iPhone.

    Versely AI Weekly

    New AI models, every Thursday.

    The image, video, audio and LLM models released that week, what each is good for, and what's new on Versely.

    Weekly. Unsubscribe anytime.