AmayaSpeak — synthetic voice evaluation

Model: facebook/mms-tts-quz (Quechua, Cusco), Meta / Massively Multilingual Speech.
Source: https://huggingface.co/facebook/mms-tts-quz
Model license: Creative Commons Attribution-NonCommercial 4.0 International.
https://creativecommons.org/licenses/by-nc/4.0/

These samples are generated audio, not recordings of a native speaker.
Processing by AmayaSpeak: native VITS speaking rate of 0.8 for short words,
200 ms of leading silence and 400 ms of trailing silence.
The player optionally slows playback while preserving pitch and repeats twice.
Detailed linguistic review is pending. No endorsement by Meta is implied.

Current use: non-commercial evaluation. Commercial permission for generated
outputs has not been established. The model's license is identified here;
this notice does not assert that every generated WAV automatically inherits it.
Before commercial deployment, resolve permissions or replace the voice source.