MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model

Matthew Baas, Pieter Scholtz, Arnav Mehta, Elliott Dyson, Akshat Prakash +1 more
1/10/2025
eess.AScs.CL

No confident code implementation found for this paper.

Abstract

Codec-based text-to-speech (TTS) models have shown impressive quality with zero-shot voice cloning abilities. However, they often struggle with more expressive references or complex text inputs. We present MARS6, a robust encoder-decoder transformer for rapid, expressive TTS. MARS6 is built on recent improvements in spoken language modelling. Utilizing a hierarchical setup for its decoder, new speech tokens are processed at a rate of only 12 Hz, enabling efficient modelling of long-form text while retaining reconstruction quality. We combine several recent training and inference techniques to reduce repetitive generation and improve output stability and quality. This enables the 70M-parameter MARS6 to achieve similar performance to models many times larger. We show this in objective and subjective evaluations, comparing TTS output quality and reference speaker cloning ability. Project page: https://camb-ai.github.io/mars6-turbo/

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

86% match2024

TTS-1 Technical Report

85% match2025

Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis

84% match1 repo1772024

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

83% match2024

Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer

82% match1 repo702024

IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

82% match1 repo21.6k2025

Cite this paper

@article{baas2025mars,
  title  = {MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model},
  author = {Matthew Baas and Pieter Scholtz and Arnav Mehta and Elliott Dyson and Akshat Prakash and Herman Kamper},
  year   = {2025},
  eprint = {2501.05787},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.05787v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.05787.svg)](https://codeofpaper.com/paper/2501.05787)

Discussion