What is voice cloning?
Voice cloning learns the sound of a voice from a short recording and reads new text with it. Record 10 to 30 seconds of yourself speaking naturally, save it as one of My voices, then type anything and hear it in your own voice.
Saved voices work across PopNow: pick My voice in AI Avatar or Lip Sync and the video speaks with your sound.
How to clone your voice
- Record or upload10 to 30 seconds of clear speech, recorded in a quiet room.
- Confirm and saveTick that the voice is yours, or that you have permission, and give it a name.
- Type and listenWrite up to 1,000 characters and download the audio.
Why clone here
- Seconds to set up. No training wait: a short sample is enough.
- Reusable. Your voice is saved to My voices for every tool.
- Pairs with video. Talking avatars and lip sync can use the same voice.
- Low cost. Each reading costs 36 credits.
What people use it for
- Voiceovers Narrate videos and slides without recording every take.
- Fixing a recording Replace one sentence instead of re-recording the whole thing.
- Messages Send a voice note when you can’t talk out loud.
- Your avatar’s voice Give your AI avatar your real sound.
Tips for a better clone
- Record in a quiet room, about a hand’s width from the microphone.
- Speak naturally, in the same tone you want the clone to use.
- Avoid music, other voices and echo in the sample.
- Short sentences with clear punctuation sound most natural.
Use it responsibly
Only use your own face and voice, or those of people who said yes. Never upload anyone under 18, and don’t use results to mislead people about who said or did something. Every request goes through PopNow’s content checks, and anything uploaded is used only to make your result.
Price
Saving a voice is free. Each reading with Chatterbox costs 36 credits for up to 1,000 characters.
Questions
Whose voice can I clone?+
Only your own, or the voice of someone who gave you permission. You confirm this before a voice is saved, and you should never use a clone to mislead people.
How long should the sample be?+
10 to 30 seconds of natural speech. Longer recordings are trimmed to the first 30 seconds.
Which languages work?+
English sounds most natural. Other languages are read too, with an English accent.
Can I use my voice in videos?+
Yes. Choose My voice in AI Avatar or Lip Sync and the video speaks with your clone.
How much does it cost?+
Saving a voice is free; each reading costs 36 credits.
Can I delete a voice?+
Yes. Saved voices can be removed from My voices at any time.
Voice sample8s