# Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus

arXiv: https://arxiv.org/abs/2604.13288 · HTML: https://mlsanity.com/paper/2604.13288/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [wav2letter++: The Fastest Open-source Speech Recognition System](https://mlsanity.com/paper/1812.07625/) (2018)
- [Findings of the IWSLT 2024 Evaluation Campaign](https://mlsanity.com/paper/2411.05088/) (2024)
- [Data Augmentation for Low-Resource Quechua ASR Improvement](https://mlsanity.com/paper/2207.06872/) (2022)
- [Evaluating Self-Supervised Speech Representations for Indigenous American Languages](https://mlsanity.com/paper/2310.03639/) (2023)
- [Huqariq: A Multilingual Speech Corpus of Native Languages of Peru for Speech Recognition](https://mlsanity.com/paper/2207.05498/) (2022)
- [Automatic Speech Recognition Advancements for Indigenous Languages of the Americas](https://mlsanity.com/paper/2404.08368/) (2024)

## Abstract (arXiv)

We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-to-speech (TTS) architectures: XTTS v2, F5-TTS, and DiFlow-TTS. Our models are trained on independent Spanish and Quechua speech datasets with heterogeneous sizes and recording conditions, and leverage bilingual and multilingual TTS capabilities to improve synthesis quality in both languages. By exploiting cross-lingual transfer, our framework mitigates data scarcity in Quechua while preserving naturalness in Spanish. We release trained checkpoints, inference code, and synthesized audio for each constitutional article, providing a reusable resource for speech technologies in indigenous and multilingual contexts. This work contributes to the development of inclusive TTS systems for political and legal content in low-resource settings.