Skip to main content

Grok TTS is xAI's text-to-speech, reading a script of up to 15,000 characters in one of 71 preset voices across 20 languages. Speech tags such as laughs and whispers are acted out, and speed runs from 0.7 to 1.5 times.

From $0.018/1,000 characters

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • 0:00 / –:––
    whispered-voice-note

    A late-night voice note in Eve with [pause], [breath] and [giggle] and one whispered line. The tags are acted out; a transcript of the audio contains only the spoken words.

    • en
    • eve
  • 0:00 / –:––
    slow-burn-chapter

    Romance narration in Rex at speed 0.9, with a [breath] before the last line and <slow> around it. The price was known before the run: the character count of the script, tags included.

    • 0.9
    • en
    • rex
  • 0:00 / –:––
    french-one-more-hour

    A playful French line in Camille, a native French voice, with language set to fr, a [chuckle] and a softened second sentence.

    • fr
    • 69smp8rm

This example starts at $0.018 per 1,000 characters. The Playground updates the estimate when you change the settings.