https://xezpeleta.github.io/en/tags/aholab/Recent content in Aholab on Xabi EzpeletaHugo -- 0.160.0enCopyright © 2021, Xabier Ezpeleta. License CC BY-SA 4.0.Sat, 04 Apr 2026 00:00:00 +0000https://xezpeleta.github.io/en/blog/euskarazko-ahots-sintesirako-ereduak/Sat, 04 Apr 2026 00:00:00 +0000https://xezpeleta.github.io/en/blog/euskarazko-ahots-sintesirako-ereduak/<p>In recent years, text-to-speech (<em>TTS</em>) models have advanced enormously. Month after month, new releases improved pronunciation, prosody, and overall audio quality. Unfortunately, most of those models were designed for English, or at best compatible with only a few languages.</p> <p>The tools available for generating Basque voices used to be quite limited: paid proprietary systems (such as <a href="https://ttsneuronala.elhuyar.eus/">Elhuyar&rsquo;s neural TTS, developed by Orai</a>), or older robotic voices that had clearly fallen behind.</p>