Clone a voice with just 10 seconds of audio. Your cloned voice stays private to your account.
For best results, use 10–30 seconds of clear speech.
Use one clear speaker in a quiet room.
Speak naturally at a steady volume.
Your first preview uses normal TTS credits · about 6 credits.
Do not upload a voice or audio you do not own or have permission to use.
Use 10–30 seconds of clear speech from one speaker. Longer files are trimmed to a 20-second clip you can adjust.
Confirm you own the voice or have permission to use it, then sign in free to create the voice model. Creating a voice uses no credits.
Type text and hear it in your cloned voice. Every preview and generation shows its exact credit cost first.
Only clone your own voice or a voice you have explicit permission to use. Never use a cloned voice for fraud, impersonation, harassment, or content that could mislead people into thinking it is a real recording.
Acceptable Use PolicyA cloned voice approximates the tone and timbre of a short sample, so results depend on recording quality. Free accounts can keep up to 5 private voices; Pay as you go and Creator plans include unlimited private voices under fair use.
Creating a private voice uses no credits, and free accounts can keep up to 5 voices. Generating speech with your voice uses credits from your balance, and free accounts get 1,200 credits every 30 days.
10 to 30 seconds of clear speech from one speaker. You can upload a file or record directly in your browser.
Only you. Cloned voices are private to your account and never appear in the public voice library.
Only with their explicit permission. Voice Cloning is for your own voice or a voice you are authorized to use. To try ready-made AI voices, browse the public voice library.
Prefer a ready-made voice? Browse celebrity and character AI voices or try free text to speech.