MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Singh, Jaskaran, Chowdhury, Amartya Roy, Prabhakar, Raghav, W, Varshul C.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909744187310080
author Singh, Jaskaran
Chowdhury, Amartya Roy
Prabhakar, Raghav
W, Varshul C.
author_facet Singh, Jaskaran
Chowdhury, Amartya Roy
Prabhakar, Raghav
W, Varshul C.
contents Current Text-to-Speech models pose a multilingual challenge, where most of the models traditionally focus on English and European languages, thereby hurting the potential to provide access to information to many more people. To address this gap, we introduce MahaTTS-v2 a Multilingual Multi-speaker Text-To-Speech (TTS) system that has excellent multilingual expressive capabilities in Indic languages. The model has been trained on around 20K hours of data specifically focused on Indian languages. Our approach leverages Wav2Vec2.0 tokens for semantic extraction, and a Language Model (LM) for text-to-semantic modeling. Additionally, we have used a Conditional Flow Model (CFM) for semantics to melspectogram generation. The experimental results indicate the effectiveness of the proposed approach over other frameworks. Our code is available at https://github.com/dubverse-ai/MahaTTSv2
format Preprint
id arxiv_https___arxiv_org_abs_2508_14049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis
Singh, Jaskaran
Chowdhury, Amartya Roy
Prabhakar, Raghav
W, Varshul C.
Audio and Speech Processing
Computation and Language
Current Text-to-Speech models pose a multilingual challenge, where most of the models traditionally focus on English and European languages, thereby hurting the potential to provide access to information to many more people. To address this gap, we introduce MahaTTS-v2 a Multilingual Multi-speaker Text-To-Speech (TTS) system that has excellent multilingual expressive capabilities in Indic languages. The model has been trained on around 20K hours of data specifically focused on Indian languages. Our approach leverages Wav2Vec2.0 tokens for semantic extraction, and a Language Model (LM) for text-to-semantic modeling. Additionally, we have used a Conditional Flow Model (CFM) for semantics to melspectogram generation. The experimental results indicate the effectiveness of the proposed approach over other frameworks. Our code is available at https://github.com/dubverse-ai/MahaTTSv2
title MahaTTS: A Unified Framework for Multilingual Text-to-Speech Synthesis
topic Audio and Speech Processing
Computation and Language
url https://arxiv.org/abs/2508.14049