Detect language from provided text, Currently supports 23 languages (English, Bangla, Manipuri, Bodo, Konkani, Oriya, Nepali, Marathi, Sindhi, Sanskrit, Malayalam, Urdu, Assamese, Telugu, Dogri, Gujarati, Kashmiri, Punjabi, Santali, Maithili, Hindi, Tamil, Kannada)

Text-to-speech models trained using FastPitch and HiFi-GAN vocoder, separately for each language. Supports both 'female' and 'male' voices.

IndicNER is a multilingual Named Entity Recognition model fine-tuned on 11 Indian languages to identify named entities in text

AI4Bharat's Indic-Trans-v2 is a multilingual Transformer (~1.1BM) NMT model trained on Samanantar v2 dataset which is the largest publicly available parallel corpora collection for languages of India at the time of writing (23 March 2023). We currently release two models - Indic to English and English to Indic and support all the 22 scheduled languages of India.

A Transformer-based multilingual transliteration model

A 1.3B parameter Transformer model trained on structured QA, NLP tasks, and Python code, optimized for text generation, summarization, and creative writing, with no fine-tuning from human feedback.

A 3.8B parameter AI model optimized for memory-efficient reasoning, instruction following, and long-context processing, designed for compute-constrained environments and latency-sensitive applications.

A lightweight AI model optimized for multilingual text generation, reasoning, and instruction adherence, designed for memory-efficient applications and generative AI tasks.