Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918487690051584 |
|---|---|
| author | Karnjanaekarin, Jullajak Trakuekul, Pontakorn Panitsrisit, Narongkorn Sumanakul, Sumana Nitayasomboon, Vichayuth Guntasin, Nithid Denkavin, Thanavin Rutherford, Attapol T. |
| author_facet | Karnjanaekarin, Jullajak Trakuekul, Pontakorn Panitsrisit, Narongkorn Sumanakul, Sumana Nitayasomboon, Vichayuth Guntasin, Nithid Denkavin, Thanavin Rutherford, Attapol T. |
| contents | We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressive TTS model. JaiTTS-v1.0 directly processes numerals and Thai-English code-switching, which is very common in realistic settings, without explicit text normalization. We test the models on short- and long-duration speech generation, which reflects many real-world use cases. JaiTTS-v1.0 achieves a state-of-the-art CER of 1.94%, surpassing the human ground truth of 1.98% for short-duration tasks while performing on par with human ground truth for long-duration tasks. In human judgment evaluations, our model wins 283 of 400 pairwise comparisons against commercial flagships, with only 58 losses. Our code and demo are available at https://github.com/JTS-AI-Team/JaiTTS . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27607 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | JaiTTS: A Thai Voice Cloning Model Karnjanaekarin, Jullajak Trakuekul, Pontakorn Panitsrisit, Narongkorn Sumanakul, Sumana Nitayasomboon, Vichayuth Guntasin, Nithid Denkavin, Thanavin Rutherford, Attapol T. Computation and Language We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressive TTS model. JaiTTS-v1.0 directly processes numerals and Thai-English code-switching, which is very common in realistic settings, without explicit text normalization. We test the models on short- and long-duration speech generation, which reflects many real-world use cases. JaiTTS-v1.0 achieves a state-of-the-art CER of 1.94%, surpassing the human ground truth of 1.98% for short-duration tasks while performing on par with human ground truth for long-duration tasks. In human judgment evaluations, our model wins 283 of 400 pairwise comparisons against commercial flagships, with only 58 losses. Our code and demo are available at https://github.com/JTS-AI-Team/JaiTTS . |
| title | JaiTTS: A Thai Voice Cloning Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.27607 |