Work

TonePick: An AI-Based Personalized Audiobook Application Using Voice Cloning and Real-Time TTS

Year: 2025

Type: article

Abstract: This paper presents TonePick, a mobile application that enables the generation of personalized audiobooks by leveraging voice cloning and real-time Text-to-Speech (TTS) synthesis. The system allows users to create a custom AI voice model using short speech samples and applies it to read PDF documents with emotional expressiveness. Built with React Native, Firebase, and the ElevenLabs API, the architecture supports scalable deployment and seamless client-server interaction. A user study involving 27 participants demonstrated high levels of satisfaction across usability, naturalness, and emotional engagement, confirming the system’s effectiveness and applicability. The proposed approach highlights the potential of voice cloning as a socially impactful extension of TTS technology.

Source: International Journal of Computer Science and Mobile Computing

DOI: 10.47760/ijcsmc.2025.v14i09.003

Authors: Seeun Kim, Jinyoung Kim, Junwoo Park, Sungsu Ahn, Seungjae Lee

Institution: Sun Moon University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion

OpenAlex ID: W4414616236

FWCI:

Cites:

Cited by:

Related to: