cs.CLNov 10, 2026

Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech

Authors: Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas

Organizations: PatientDesk AI

Abstract

Antalia-2 Mini is a single-voice Turkish text-to-speech model with 7,620,931 parameters. It reads characters and produces 48 kHz audio at 41 times real time on an Apple M5 laptop CPU (2 threads). Its training audio came only from VoxCPM2 (the teacher), about 300 times larger, cloning one synthetic clip; automatic checks kept about 1,790 h. Fine-tuning the vocoder on the acoustic model's own mel spectrograms cut the word error rate (WER) of Whisper's transcripts from a mean of 3.89% to 1.75% at adjacent pre-release checkpoints. The teacher corrupts the start of a clip when the first word begins with ö, the student learned this, and a spoken prefix we cut from the output hides it. On the 495-sentence Freya-TR-Eval benchmark, where we tuned settings, version 1.0.1 has WER 1.09% and character error rate 0.22% on our public harness. A paired bootstrap cannot distinguish these from EMA Lightning, an 8.6M Turkish model, which scores higher on full-band UTMOS, an English-trained quality proxy. No human listening test exists. Weights, inference code and the benchmark harness are public under Apache-2.0; training code and data are not.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloning

    Nov 10, 2026Sezgin Saygili, Emre Kaplaner, Oncel Ozgul +1TTS SynthesisVoice Cloning

  2. FreyaTTS Technical Report

    Jul 10, 2026Ahmet Erdem Pamuk, Ömer Yentür, Ahmet Tunga Bayrak +2Non-Autoregressive Text GenerationTTS Synthesis