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.
Figures & tables
Figure 1: Spanish and Quechua Text to Speech Model.
Model
#Params
UTMOS ↑
SIM-O ↑
WER ↓
RMSEF0↓
RMSEE↓
XTTS-V2
470M
3.22
0.53
0.19
21.03
0.021
F5-TTS
336M
3.23
0.60
0.19
15.17
0.017
DiFLOW-TTS
164M
3.31
0.49
0.16
10.24
0.011
Table 1: Objective and perceptual evaluation of Quechua synthesized speech using constitutional text as input. All metrics are computed on audio generated from Quechua text of the Constitution, leveraging cross-lingual training with Spanish as a high-resource language. Higher is better for UTMOS and SIM-O, while lower is better for WER, RMSE F0 , and RMSE E .
Xingchen AGI Lab, China Telecom Artificial Intelligence Technology Co. Ltd · Qinghai Normal University, Xining, China · University of Electronic Science and Technology of China,Chengdu,China +1