॥ वाचं धेनुमुपासीत ॥

Vāgdhenu

A vṛtta (meter) aware śloka-to-chant text-to-speech system for Sanskrit.

Prof. Prathosh A P · Indian Institute of Science, Bengaluru · prathosh@iisc.ac.in

Try it

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 ↗.

Listen — sample chants

Six vṛttas rendered by this system — including verses from the shipped deployments.

vasantatilakā Mahābhārata Tātparya Nirṇaya · 1.1

नारायणाय परिपूर्णगुणार्णवाय विश्वोदयस्थितिलयोन्नियतिप्रदाय ।
ज्ञानप्रदाय विबुधासुरसौख्यदुःखसत्कारणाय वितताय नमोनमस्ते

śārdūlavikrīḍita Śrīmad Bhāgavatam · 1.1.2

जन्माद्यस्य यतोऽन्वयादितरतश्‍चार्थेष्वभिज्ञः स्वराट् तेने ब्रह्म हृदा य आदिकवये मुह्यन्ति यं सूरयः। तेजोवारिमृदां यथा विनिमयो यत्र त्रिसर्गो मृषा धाम्ना स्वेन सदा निरस्तकुहकं सत्यं परं धीमहि

anuṣṭubh Śrīmad Bhāgavatam · 1.1.5

नैमिषेऽनिमिषक्षेत्रे ऋषयः शौनकादयः। सत्रं स्वर्गाय लोकाय सहस्रसममासत

vaṃśastha Śrīmad Bhāgavatam · 1.3.5

पश्यन्त्यदो रूपमदभ्रचक्षुषः सहस्रपादोरुभुजाननाद्भुतम्। सहस्रमूर्धश्रवणाक्षिनासिकं सहस्रमौल्यम्बरकुण्डलोल्‍लसत्

drutavilambita Śrīmad Bhāgavatam · 1.1.4

निगमकल्पतरोर्गलितं फलं शुकमुखादमृतद्रवसंयुतम्। पिबत भागवतं रसमालयं मुहुरहो रसिका भुवि भावुकाः

mālinī Narasiṃha stuti · retroflex tongue-twister

हठलुठ दल घिष्टोत्कण्ठदष्टोष्ठ विद्युत् सटशठ कठिनोरः पीठभित्सुष्ठुनिष्ठाम् ।
पठतिनुतव कण्ठाधिष्ठ घोरान्त्रमाला दह दह नरसिंहासह्यवीर्याहितं मे ॥

About

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.

Deployments

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 ↗