Skip to main content

elevenlabs/v4/text-to-speech

Eleven v4 is ElevenLabs' text-to-speech model for turning a script into single-speaker audio. This endpoint combines premade voice selection with language, delivery and export controls.

From $0.096/1,000 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 / –:––
    Late-night storytelling intro in the George voice

    George read 126 characters with stability 0.4 and mp3_44100_128; the result is an 8.75-second mono MP3, and the [softly] cue shapes the delivery without being pronounced.

    • George
    • 0.4
    • mp3_44100_128
  • 0:00 / –:––
    Museum notice read by Daniel with a whisper cue

    Daniel, language en, seed 7 and mp3_22050_32 produced this 5.17-second file at 22.05 kHz and 32 kbps; the [whispers] tag itself is not spoken aloud.

    • 7
    • en
    • Daniel

This example starts at $0.096 per 1,000 characters. The Playground updates the estimate when you change the settings.