Official BytePlus partnerBuilt on BytePlus, ByteDance's official AI platform
AI voice cloning
AI voice cloning for your own voice, with consent
Clone your own voice from 10 to 30 seconds of clean speech and use it in Text to Speech. You confirm consent before every clone, KreatorFlow records it, and voices of public figures are not allowed.
- 10 to 30 second sample
- Consent recorded
- Your voice only
- 50 credits per clone
Consent comes first
You can clone your own voice, or a voice whose owner has given you explicit written permission. Before every clone you tick a box confirming that, the clone is refused without it, and KreatorFlow stores the date and time of that confirmation with the voice.
Voice names that point to a public figure, celebrity or politician are refused before anything is stored or charged. The voice cloning rules in the Acceptable Use Policy apply to every cloned voice, and KreatorFlow may remove voices and suspend accounts that break them.
How it works
- 1
Record or upload a sample
About 10 to 30 seconds of clean speech from one speaker. Record in the browser or upload WAV, MP3 or M4A, up to 20 MB.
- 2
Name it and confirm consent
Give the voice a name, choose its language and confirm that it is your voice or that you have permission.
- 3
Use it in Text to Speech
When training finishes the voice appears under My Voices and reads any script like the built-in voices.
What is not allowed
- Voices of public figures, celebrities or politicians without their written permission
- Impersonating anyone, or deceiving listeners about who is speaking
- Fraud, scams and fake endorsements
- Political deepfakes, such as invented statements by candidates or officials
- Voices of minors
Tips for a clean sample
Record in a quiet room, close to the microphone, and speak naturally at your normal pace. One speaker only, with no music or background noise. Read a varied paragraph rather than a single repeated phrase, so the clone hears the full range of your voice.
Pricing
A clone costs 50 credits, charged once. Speech made with your cloned voice then costs the normal Text to Speech price of 1 credit per 1,000 characters. If training fails, the credits are refunded.
Voice cloning questions
Whose voice can I clone?
Your own, or the voice of someone who has given you explicit written permission to clone it and use it the way you intend. Never a public figure, celebrity, politician or minor.
What happens to my consent?
The clone cannot start until you confirm consent, and KreatorFlow stores the date and time of that confirmation with the cloned voice. It can be used to look into reports of misuse.
How long should the sample be?
About 10 to 30 seconds of clean speech from one speaker. Uploads can be up to 20 MB before conversion.
How much does a clone cost?
50 credits per clone, once. Using the voice costs 1 credit per 1,000 characters, like any other voice.
What if someone cloned my voice without permission?
Report it to support. Cloning without permission breaks the Acceptable Use Policy, and KreatorFlow may remove the voice and suspend the account.
Which platform does the audio studio run on?
Built on BytePlus, ByteDance's official AI platform. KreatorFlow is an official BytePlus partner; the audio studio and its credit prices are KreatorFlow's own.
Clone your own voice
Record 10 to 30 seconds, confirm consent and use your voice in Text to Speech.