cd /news/artificial-intelligence/vagdhenu-open-source-meter-aware-tex… · home topics artificial-intelligence article
[ARTICLE · art-44414] src=prathosh.in ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

Vāgdhenu: Open-source meter-aware text-to-speech for Sanskrit

Vāgdhenu, an open-source meter-aware text-to-speech system for Sanskrit, automatically detects verse meters and generates chant recitations. Developed by retraining a flow-matching TTS backbone on a custom 5-hour Sanskrit chant corpus, it achieves an expert MOS of 4.6 and correctly renders complex conjuncts. The system has produced two large-scale corpora: the Mahābhārata Tātparya Nirṇaya (5,183 verses) and the Śrīmad Bhāgavatam (~18,000 verses).

read1 min views1 publishedJun 30, 2026

Paste a Sanskrit verse in any Indian script — the meter is detected automatically.

First chant takes ~10–60s while the model warms up. If the demo doesn't load,

use the backup demo ↗. Six vṛttas rendered by this system — including verses from the shipped deployments.

Vāgdhenu maps a metrical verse to its chanted pārāyaṇa recitation. Its voice is a flow-matching TTS backbone retrained on a purpose-recorded, carefully designed single-speaker Sanskrit chant corpus (~5 hours), with a further voice-steering retrain; the neural vocoder is likewise fine-tuned for the chant register. Around the trained model sits the machinery a faithful Sanskrit chant pipeline needs: a script-aware frontend that routes Sanskrit through Kannada orthography (avoiding the Hindi schwa-deletion that Devanagari triggers); visarga sandhi with the jihvāmūlīya and upadhmānīya allophones; the aspiration contrast; the three sibilants and the full retroflex series kept distinct; homorganic anusvāra and vocalic ṝ; and a vṛtta-aware mechanism that detects the meter and selects a matched reference under the half-reference rule. The retrained model reaches an expert MOS of about 4.6, and dense conjuncts — including retroflex aspirates — render correctly, the class earlier architectures could not crack.

This system produced two corpora at scale.

Mahābhārata Tātparya Nirṇaya — 32 chapters, 5,183 verses (~17.5h) ·

video series ↗Śrīmad Bhāgavatam — ~18,000 verses across 12 books · karaoke-video series ↗

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @vāgdhenu 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/vagdhenu-open-source…] indexed:0 read:1min 2026-06-30 ·