One thing first

Only copy a voice you're allowed to copy.

This page can make a voice say things it never said. That is useful, and it is also easy to misuse. Two boxes, then you're in.

Read the full terms
  1. Your voice, or permission. You will only use a recording of your own voice, or of someone who has knowingly and freely given you permission to clone theirs. You will not use a recording taken from a video, a broadcast, a phone call, a public figure, or anyone who has not agreed.
  2. No impersonation. You will not use anything made here to impersonate a real person, to deceive anyone into believing they are hearing that person, to authenticate yourself to a voice-secured system, or to defraud, harass, defame, or harm anyone.
  3. No unlawful use. Cloning a voice without consent may be illegal where you live. Several jurisdictions treat a voice as protected biometric data, or grant a right of publicity in it. Complying with the law where you are is your job, and you accept that responsibility.
  4. Label what you make. If you publish or send audio generated here, you will identify it as synthetic. Files you download are named with an AI-GENERATED marker to help you do that.
  5. You carry the liability. You are solely responsible for what you record, generate, keep, and share. To the fullest extent the law allows, the author, operator, and host of this page bear no liability for your use of it, and you will hold them harmless from any claim arising out of that use.
  6. No warranty, no advice. Everything here is provided as is, with no warranty of any kind. Nothing on this page is legal advice.

Nothing you record or generate is uploaded. Audio is processed on your device and stored only in this browser. The speech model is downloaded from Hugging Face on first use and cached locally.

Voice Lab.

  1. Speak
  2. Write
  3. Hear

Step 1 of 3

Read this out loud.

Ten seconds is all it needs. Say it the way you'd say it to a friend.

Tap to start

A voice memo works well. M4A, MP3, WAV or AAC — five to ten seconds of one person talking, close to the mic.

Getting ready in the background…