Unlimited Seedance, Kling, Wan and Seedream 5.0, now on KreatorFlow · available now · Fair use

See passes
KREATORFLOW
Log inSign up

Official BytePlus partnerBytePlus, a ByteDance company

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
  • 60 credits per clone
Clone your voiceRead the voice cloning rules

One clone = 60 credits, covered by an $8 credit pack (160 credits), no subscription.

Last updated

On this page
  1. Consent comes first
  2. How it works
  3. What is not allowed
  4. Tips for a clean sample
  5. Pricing
  6. Questions other voice cloning pages skip
  7. Voice cloning questions
  8. Keep exploring

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. 1

    Check you are allowed to clone the voice

    Read the voice cloning rules first. You can clone your own voice, or a voice whose owner has given you explicit written permission; never a public figure without that permission, and never a minor.

    Section 4, Voice Cloning, of the KreatorFlow Acceptable Use Policy: own voice or written permission only, no public figures, impersonation or minors, and what happens when a voice is deleted
    Screenshot of kreatorflow.ai, 2026-10-25
  2. 2

    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.

    Voice Replication sample panel: about 10 to 30 seconds of clean solo speech, Upload audio or Record a sample, WAV, MP3 or M4A
    Screenshot of kreatorflow.ai, 2026-10-25
  3. 3

    Name it and confirm consent

    Give the voice a name, choose its language and tick the box confirming that it is your voice or that you have explicit written permission. The clone cannot start without it, and the cost is shown before you press Clone voice.

    Voice name and language fields, the box to tick saying I own this voice or have explicit written permission to clone it, and the cost shown before Clone voice
    Screenshot of kreatorflow.ai, 2026-10-25
  4. 4

    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 60 credits, charged once. Speech made with your cloned voice then costs the normal Text to Speech price of 2 credits per 1,000 characters. If the clone cannot be created, for example the sample is rejected, the credits are refunded automatically.

Questions other voice cloning pages skip

What people ask before they clone: other people's voices, deleting a voice, refunds, languages, talking videos and free accounts.

Can I clone a family member's, client's or co-host's voice?

Only with their explicit written permission to clone it and to use it the way you intend, and never a minor's voice. You tick a box before every clone confirming that you have it, KreatorFlow records the date and time, and that record can be used to look into a report. Keep the written permission yourself: it is what shows the voice was cloned with consent.

Source: Acceptable Use Policy, section 4: Voice Cloning

What happens to my recording when I delete a cloned voice?

The voice stops working at once, and its sample and photo are deleted from our storage. The voice model held by our AI provider is replaced when its slot is reused. What stays is a short record that consent was given, with no audio and no voice name, for 12 months, counted from when the cloned voice was deleted, so abuse reports can still be checked.

Source: Acceptable Use Policy, section 4: Voice Cloning

Do I get the credits back if a clone fails?

If the clone cannot be created, for example the sample is rejected or the service is busy, the 60 credits come back automatically. A voice name that points to a public figure, a missing consent tick, or a file that is not audio or is far longer than 30 seconds is stopped before anything is charged.

Which languages can I clone a voice in?

You choose the sample's language from 14: English, Mandarin, Japanese, Spanish, Portuguese, Indonesian, French, German, Korean, Italian, Thai, Vietnamese, Russian and Arabic. Record 10 to 30 seconds in the language the voice will mostly speak, in your normal speaking style.

Can I use my cloned voice in a talking video?

Yes. Make a voice line with your clone in Text to Speech and pick it as the audio in Lip Sync, which turns one photo and a voice track into a talking video, or download the audio for your own edit. The same consent rules apply wherever the voice is used.

Can I clone my voice on a free account?

The Audio studio is open on every plan and pays per use with credits, but a clone costs 60 credits and a new free account starts with 25, so the starter credits alone do not cover one. Any credits on the account count, including bonus credits, a credit pack or a plan's monthly credits, and the cost is shown next to the Clone voice button before you confirm.

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?

60 credits per clone, once. Using the voice costs 2 credits 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, a ByteDance company. KreatorFlow is an official partner of BytePlus, a ByteDance company; 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.

Clone your voiceRead the voice cloning rules

Keep exploring