Skip to main content
Voice Design

Cartesia Instant Voice Clone

Create a reusable private voice from a short recording with Cartesia Instant Voice Cloning

Try it in AmpereView details

Inputs

Loading input fields...
Execution Steps

Loading workflow structure...

Loading curated examples...

Overview

Cartesia Instant Voice Clone creates a private, reusable voice from a short recording, saves it to your Organization, and plays an audition so you can hear the result. Use the saved voice in Cartesia Sonic 3.6 Speech Generator for narration, ads, demos, and other branded audio, and clone only voices you have permission to use.

Use cases

  • Save an approved founder or spokesperson voice for product demos and launch videos.
  • Create a consistent narrator voice for a podcast, course, or explainer series.
  • Audition a cloned voice before using it in ads or social video voiceovers.

Input tips

  • Record 10 to 60 seconds of one speaker who has approved the clone, in a quiet room with no music or other voices.
  • Upload FLAC, MP3, OGG, WAV, or WebM audio up to 16 MB.
  • Give the voice a clear name so teammates can find it in the voice picker later.
  • Add a short description, such as the speaker's role or the intended use, when it helps teammates choose.
  • Set language to the language the voice will speak; for any language other than English, write audition text of up to 500 characters in that language.

Expected output

The AI Tool returns the saved voice's name, voice ID, and creation time, plus an audition clip you can play. If the audition cannot be made, the voice is still saved and the result explains that the preview is unavailable.

Caveats

  • Clone only voices you have clear permission to use.
  • Background noise, music, or more than one speaker lowers clone quality.
  • Cloned voices are private to your Organization and cannot be shared with other Organizations.
  • Listen to the audition before using the voice in published work.

Related AI Tools