Talking Book Service
Produce a talking book from EPUB, TXT, PDF or DOCX at roughly one point per second of audio, split into chapters with an SRT file for each one.
Step-by-step guide
How to Use Talking Book Service
Start for free — no credit card, no software to install.
Upload the title
Add an EPUB, TXT, PDF or DOCX with real text; a scan without a text layer will be rejected, since there's no OCR step.
Assign a voice
Pick one voice to narrate the whole book from the 200+ available, or design one by description.
Generate and download by chapter
Each chapter downloads as its own MP3 or WAV file, with an SRT alongside it.
Why creators choose this tool
Talking Book Service — Features & Capabilities
Everything you need to create professional voiceovers — in one tool.
Point-based cost
Audio costs roughly one point per second, so a book's price scales with its length rather than a flat per-title fee.
Automatic chapter splitting
An uploaded EPUB, TXT, PDF or DOCX is divided into chapters, each downloadable on its own.
MP3 or WAV, plus SRT
Every chapter exports as MP3 or WAV, with a matching SRT caption file.
One voice across a whole title
The same voice narrates every chapter of a book, keeping the listening experience consistent title to title.
Use cases
What Can You Create with Talking Book Service?
From TikTok to podcasts — here's where creators use this tool most.
Starting a small talking-book collection
A library or charity testing demand can produce a handful of titles first, checking turnaround and cost before committing to a larger catalogue.
A member request for a specific title
One title requested by a reader converts on its own timeline, without waiting for a batch of other books to be ready.
Digitising a backlist already in text form
Titles that exist as EPUB or a text-based PDF convert directly; anything scanned from a physical book needs a text layer added first.
Multiple chapters, one voice
A whole book keeps one consistent voice across every chapter, useful for a listener working through a title over several sittings.
vs Standard TTS
Vocallab vs Standard Text-to-Speech
See why creators switch from generic TTS tools to Vocallab.
About this tool
Everything you need to know about Talking Book Service
A talking book service uses this to turn a title into narrated audio at the per-character cost of the underlying text-to-speech engine, roughly one point per second of finished audio. A typical novel-length book runs several hours of audio, so the point cost scales with length rather than with a flat per-title fee. Upload an EPUB, TXT, PDF or DOCX, with a real text layer since no OCR is available, and the file is split into chapters automatically; each chapter narrates in the same voice, ready to download as MP3 or WAV with an SRT file per chapter.
People also search for
FAQ
Talking Book Service — FAQ
Common questions users ask about the Talking Book Service voice. If you need additional help, please contact us via the contact form or email us at support@vocallab.ai.
How much does a book cost to produce?
Roughly one point per second of finished audio, so a full-length novel running several hours costs proportionally more than a short title — there's no flat per-book fee.
How long does a title take to produce?
Generation time scales with the book's length; a novel-length title runs to several hours of audio once every chapter has generated.
Can a scanned older book be converted?
Not directly — there's no OCR here, so a scanned file needs a text layer added elsewhere before it can be uploaded.
Does every chapter use the same voice?
Yes, one voice is assigned per title and narrates every chapter, keeping the whole book consistent.
What file formats come out?
MP3 or WAV per chapter, each with a matching SRT caption file.
More in this collection
Related AI Voice Tools
Accessible Course Materials
Convert course readings and handouts with a text layer into MP3 with captions, triaged and costed for a disability-services team's deadlines.
AccessibilityText to Speech for Accessibility
Turn written text into an MP3 with an SRT caption file, from 200+ voices. This produces audio files from text you control — it is not assistive software.
AccessibilityAudio Signage for Venues
Generate short spoken signs for wayfinding, exhibits and safety notices as individual MP3 files, in as many languages as your venue needs.
AccessibilityAccessible PDF to Audio
A scanned PDF is rejected outright — there's no OCR here. Upload a PDF with a real text layer instead and get an MP3 with SRT captions, split by heading.
AccessibilityScreen Reader Alternative
Not a screen reader — it can't navigate a page or announce controls. It turns text you already have into an MP3 with SRT captions to listen to later.
AccessibilityPatient Information Audio
Turn approved patient leaflets and discharge notes into audio with captions. Reads your text exactly as written, word for word — no clinical claims.