AI-Powered Multi-Voice Book Narration

Story Narration

Upload a chapter, let the model cast each character with a distinct voice, and watch the scene unfold turn-by-turn with synchronized narration, a color-coded timeline, and a live script.

Now playing · The Wonderful Wizard of Oz · L. Frank Baum
0:00 / 2:03
2:03Total length
19Turns
3Voices
Gemini TTSEngine

Turn Timeline

0s1:012:03

Synchronized Script

Source → Narration

Original PDF page
The input — a scanned chapter from The Wonderful Wizard of Oz.
Multi-voice narration
19 turns · 3 voices · 2:03
Gemini LLM splits the prose into speaker-tagged turns, a voice is cast per character, and each line is rendered with Gemini TTS — timings come straight from the per-segment WAVs.

Cast & Voices

N
Narrator
Voice Charon · Narration
Steady storytelling voice
9 turn(s) · 72.8s · 59.2%
W
Witch of the North
Voice Autonoe · female
Elderly, sweet-voiced, calm, benevolent witch, friend to the Munchkins
6 turn(s) · 32.3s · 26.3%
D
Dorothy
Voice Leda · female
Innocent, young girl, confused and curious about her new surroundings
4 turn(s) · 13.9s · 11.3%
How it works

Story Narration

Overview

Story narration demonstrates how AI can be used to generate a multi-character audiobook with different unique voices, from your favorite book PDF

Business Applications
1
Speech generation
LLM and TTS integration facilitates speech-aware chatbots and embodied AI hardware, such as automated service terminals.
High-Level Technical Workflow
1
Characters Mapping & Dialogue Formatting
Given the PDF/book text, the LLM maps the story's characters with the most suitable voice from a predefined list of voices with distinct personalities. Then it generates a dialogue-like version of the text.
2
Generating Audio Segments
The dialogue is passed in chunks to the TTS model, resulting in multiple WAV files.
3
Audio Manipulation
The chunks are concatenated into a single file. The audio is cleaned if needed and delivered to the user with a live transcription and a character map.