KREATORFLOW
Log inSign up

Official BytePlus partnerBuilt on BytePlus, ByteDance's official AI platform

AI audiobook narrator

AI audiobook narrator for long-form text to speech

Narrate chapters, articles and stories with steady narration voices. Each generation takes up to 5,000 characters, so a book is narrated in parts, chapter by chapter, with the same voice and settings every time.

  • 5,000 characters per generation
  • 13 narration voices
  • 1 credit per 1,000 characters
Start narratingBrowse the voice library

How to split a book into parts

  1. 1

    Clean the text

    Remove page numbers, running headers, footnote markers and anything else the narrator should not read.

  2. 2

    Cut each chapter into parts of up to 5,000 characters

    Cut at a paragraph or scene break, never mid-sentence, and number the parts (01-01, 01-02) so they stay in order.

  3. 3

    Lock the voice and settings

    Pick one narration voice and note its speed, pitch and volume. Use exactly the same settings for every part of the book.

  4. 4

    Generate, check and join

    Listen to each part, regenerate any that miss, then download the parts and join them per chapter in your audio editor.

Narration voices

The voices of the studio's "Great for narration" collection: clear, steady voices for long-form reads in 9 languages, under their real studio names.

What a chapter costs

A full 5,000-character part costs 5 credits, so a chapter of 20,000 characters, 4 full parts, costs 20 credits. Text to Speech costs 1 credit per 1,000 characters with a minimum of 1 credit per clip, the studio shows the cost before you generate and failed clips are refunded automatically.

Tips for a natural long read

  • Spell unusual names the way they sound, and keep that spelling the same in every part.
  • Write numbers, dates and abbreviations the way the narrator should say them.
  • Keep paragraph breaks: they give the narrator natural places to pause.
  • Slow the speed a touch for dense non-fiction and leave it at normal for fiction.
  • For a scene between two characters, two-speaker mode gives each one a voice.

Narrate text you have the rights to

Narrate your own writing, public-domain texts, or books whose audio rights you hold or have licensed. If you narrate with a cloned voice, it must be your own voice or one you have explicit written permission to clone.

AI audiobook questions

How much text can one generation take?

Up to 5,000 characters. Longer chapters are split into parts and joined after download.

How do I keep the voice consistent across a book?

Use the same preset voice with the same speed, pitch and volume for every part. Preset voices sound the same every time.

Which languages can I narrate in?

The narration voices cover 9 languages, and every one of the 14 Text to Speech languages has at least one voice you can narrate with.

Can I narrate with my own voice?

Yes. Clone your own voice from 10 to 30 seconds of clean speech for 60 credits, with consent recorded, and use it for every part.

What does a chapter cost?

A full 5,000-character part costs 5 credits, so a chapter of 20,000 characters costs 20 credits.

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.

Narrate your first chapter

Pick a narration voice, paste up to 5,000 characters and generate. 1 credit per 1,000 characters.

Start narratingBrowse the voice library

Keep exploring