Skip to main content

elevenlabs/voice-changer/audio-to-audio

ElevenLabs Voice Changer is ElevenLabs' speech-to-speech tool for converting a recording into a different premade voice. This audio-to-audio endpoint takes up to 5 minutes of speech and returns an MP3 with the source words and timing.

From $0.0048/s

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 / –:––
    Harbor tour narration converted to the Brian voice

    Brian with background-noise removal off; the 4.50-second MP3 at 44.1 kHz, mono and 128 kbps keeps every word of the source sentence.

    • Brian
  • 0:00 / –:––
    Same harbor narration converted to the Matilda voice

    Matilda on the same source WAV with noise removal off returned another 4.50-second MP3, and a local transcript matched the original sentence word for word.

    • Matilda

This example starts at $0.0048 per output second. The Playground updates the estimate when you change the settings.