Official BytePlus partnerBuilt on BytePlus, ByteDance's official AI platform
Guide · Audio
How to clone your voice safely with AI
Clone your own voice with consent: 10 to 30 seconds of clean speech, the confirmation KreatorFlow records, what is not allowed and tips for a clean sample.
- 10 to 30 s sample
- Consent recorded
- 60 credits per clone
Short answer
Record 10 to 30 seconds of your own voice, clean and free of noise, confirm consent and clone it in Voice Replication for 60 credits. Only clone your own voice or one you have explicit written permission for; never public figures, minors or impersonation.
Updated:
Step by step
- 1
Check whose voice it is
Your own voice, or the voice of someone who has given you explicit written permission to clone it and use it the way you intend. Nothing else.
- 2
Record a clean sample
10 to 30 seconds of one speaker in a quiet room. Record in the browser or upload a file of up to 20 MB.
- 3
Name it
Your own descriptive name, such as "My narration voice". Names that point to a public figure, celebrity or politician are refused before anything is stored or charged.
- 4
Confirm consent
Tick the box that confirms the voice is yours or that you have permission. Without it the clone does not start, and KreatorFlow stores the date and time of that confirmation with the voice.
- 5
Use it in Text to Speech
When training finishes, the voice appears under "My Voices" and reads any script at 1 credit per 1,000 characters.
What is not allowed
The voice cloning rules in the Acceptable Use Policy apply to every cloned voice. KreatorFlow may remove voices and suspend accounts that break them.
- 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
The quality of a clone depends mostly on the sample.
- A quiet room without echo, close to the microphone.
- One speaker only, with no music or background noise.
- Speak naturally at your normal pace.
- Read a varied paragraph rather than repeating one phrase.
- Keep the length between the recommended minimum and maximum.
If someone cloned your voice without permission
Report it to support. Cloning without permission breaks the Acceptable Use Policy, and the consent record stored with every voice helps look into the report.
Frequently asked questions
Whose voice can I clone?
Your own, or the voice of someone who has given you explicit written permission. Never a public figure, celebrity, politician or minor.
How long should the sample be?
10 to 30 seconds of clean speech from one speaker. Uploads can be up to 20 MB before conversion.
How much does it cost?
60 credits per clone, once. Using the voice costs 1 credit per 1,000 characters. If training fails, the credits are refunded.
Try it in the studio
New accounts get 75 starter credits for images and video. Free accounts can make video on Seedance 2 Fast and Seedance 2.0 Mini at 480p, queued and rate limited. A plan adds every video model, 720p and above, and no queue. The cost is shown before every generation.