Vāgdhenu: A Sanskrit Chanting TTS System
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.
नारायणाय परिपूर्णगुणार्णवाय विश्वोदयस्थितिलयोन्नियतिप्रदाय ।
ज्ञानप्रदाय विबुधासुरसौख्यदुःखसत्कारणाय वितताय नमोनमस्ते
जन्माद्यस्य यतोऽन्वयादितरतश्चार्थेष्वभिज्ञः स्वराट् तेने ब्रह्म हृदा य आदिकवये मुह्यन्ति यं सूरयः। तेजोवारिमृदां यथा विनिमयो यत्र त्रिसर्गो मृषा धाम्ना स्वेन सदा निरस्तकुहकं सत्यं परं धीमहि
नैमिषेऽनिमिषक्षेत्रे ऋषयः शौनकादयः। सत्रं स्वर्गाय लोकाय सहस्रसममासत
पश्यन्त्यदो रूपमदभ्रचक्षुषः सहस्रपादोरुभुजाननाद्भुतम्। सहस्रमूर्धश्रवणाक्षिनासिकं सहस्रमौल्यम्बरकुण्डलोल्लसत्
निगमकल्पतरोर्गलितं फलं शुकमुखादमृतद्रवसंयुतम्। पिबत भागवतं रसमालयं मुहुरहो रसिका भुवि भावुकाः
हठलुठ दल घिष्टोत्कण्ठदष्टोष्ठ विद्युत् सटशठ कठिनोरः पीठभित्सुष्ठुनिष्ठाम् ।
पठतिनुतव कण्ठाधिष्ठ घोरान्त्रमाला दह दह नरसिंहासह्यवीर्याहितं मे ॥
Get the app
These recitations power a free app for the complete Śrīmad Bhāgavatam.
॥ भागवतवाणी ॥
Bhāgavata-VāNi
The complete Śrīmad Bhāgavatam — all 12 skandhas — with synced audio recitation and line-by-line karaoke highlighting, in 10 Indian scripts. Search any verse in any script, traditional indices, works fully offline. Free, no ads.
Practise with it
Vāgdhenu's chants power a companion tool that listens to you.
॥ वाग्बोधिनी ॥
Vāgbodhinī
A Sanskrit chant tutor. Paste any śloka (or prose) in any script, hear its metre-aware reference chant rendered by Vāgdhenu, then chant along — a Sanskrit speech model scores every syllable and shows you what to fix. For classical (laukika) Sanskrit.
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 ↗
Source: hackernews