Metraipolis › archive › dc_ebf5d00fc4c3

Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrit — arXiv:2608.26146

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26146
License (as archived)
CC0-1.0
Archived
2026-10-17T15:18:40.411Z
SHA-256 of the archived text
5f6a7b4583caad8783d90941ca13053886e1addcceb5ead199e1ff84f5369fbb
Stable URL of this page
https://metraipolis.com/documento/dc_ebf5d00fc4c3

How to cite

Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrit — arXiv:2608.26146 — arXiv (en), https://arxiv.org/abs/2608.26146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebf5d00fc4c3 (Metraipolis archive dc_ebf5d00fc4c3, sha256 5f6a7b4583caad8783d90941ca13053886e1addcceb5ead199e1ff84f5369fbb)
BibTeX
@misc{dcebf5d00fc4c3,
  title = {Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrit — arXiv:2608.26146},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26146},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebf5d00fc4c3; sha256 5f6a7b4583caad8783d90941ca13053886e1addcceb5ead199e1ff84f5369fbb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present Vagdhenu, a vrutta (meter) aware shloka-to-chant system for Sanskrit: a text-to-speech system that maps a metrical verse to its chanted parayana recitation at high fidelity. This is an experience report, not a new architecture. We take an off-the-shelf flow-matching TTS backbone and a large-scale neural vocoder, and add the components a faithful Sanskrit chant pipeline needs: a frontend that routes Sanskrit through Kannada orthography to avoid the Hindi-style schwa deletion that Devanagari triggers in Indic models; a frontend that obeys subtle Sanskrit phonology (visarga sandhi with its jihvamuliya and upadhmaniya allophones, the aspiration contrast of alpaprana and mahaprana, and the dental, retroflex, and palatal sibilants kept distinct); and a vrutta-aware mechanism that detects the meter and picks an exactly matched reference under a half-reference rule. We report a negative result that shaped the system: in a self-infilling flow-matching backbone, a text-side prosody conditioner is architecturally inert, because the model recovers pitch from the context mel and the embedding gets no gradient; the reference clip and a voice-steering retrain are the only working prosody levers. We also report a comparative lineage across four families (StyleTTS2, VITS2, Matcha-TTS, and the flow-matching backbone), where each earlier family hit a ceiling on conjuncts or prosody that a five-hour clone cleared at an expert MOS near 4.6. The system shipped two deployments: a 32-chapter, 5183-verse video corpus (about 17.5 hours) and an audio app covering about 18000 verses across 12 books. We release the frontend, inference and training code, weights, a single-speaker chant dataset, and an interactive demo.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.26146 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:15:18.037Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).