Official BytePlus partnerBytePlus, a ByteDance company
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
- 2 credits per 1,000 characters
Last updated
On this page
How to split a book into parts
- 1
Clean the text
Remove page numbers, running headers, footnote markers and anything else the narrator should not read.
- 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
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
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 10 credits, so a chapter of 20,000 characters, 4 full parts, costs 40 credits. Text to Speech costs 2 credits per 1,000 characters with a minimum of 2 credits 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.
Text to speech by language
One page per language with at least two preset voices: its voices, tips and common questions. Also in Text to Speech, with one voice each: Italian (Matteo), Vietnamese (Mai) and Thai (Napha).
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 10 credits, so a chapter of 20,000 characters costs 40 credits.
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.
Narrate your first chapter
Pick a narration voice, paste up to 5,000 characters and generate. 2 credits per 1,000 characters.
Keep exploring
- AI voice generator
- AI text to speech
- AI voice cloning
- Multilingual text to speech
- AI voice translator
- AI voiceover generator
- AI podcast voices
- Add a voiceover to an AI video
- Clone your voice safely
- Timestamped audio prompts
- Two-speaker AI dialogue
- AI audio studio
- Add a voiceover to an AI video
- Seedance 2.0 video generator (native audio)
- Seedance 2.5 video generator (native audio)
- Guides
- Acceptable Use Policy