
Institute · Mumbai, India
BharatGen
An India-wide consortium anchored at IIT Bombay that releases open-weight text, speech and vision models for Indian languages.
Mumbai, India
- Type
- Institute
- Based in
- Mumbai, India
- Featured projects
- 7
About
BharatGen is a Section 8 not-for-profit company, the BharatGen Technology Foundation, anchored at IIT Bombay and drawing on nine consortium institutions. It is backed by India's Department of Science and Technology and the IndiaAI Mission.
A blog post dates its launch to October 2024. Its models include Param2, a 17B text model, the Sooktam text-to-speech and Shrutam speech-to-text families, and the Patram vision-language models.
Mission and ambitionsIts stated slogan is built from scratch, open weights, made for India.
Known for
- 01
Param open-weight Indian language models
- 02
Sooktam speech synthesis and Shrutam recognition
- 03
Patram vision-language models
Milestones
- 2024
First models demonstrated
Foundational models were announced at the India Mobile Congress on October 17, 2024.
- 2024
BharatGen launched
The programme was launched in New Delhi.
- 2025
Param-1 released
A 2.9 billion parameter bilingual base model described as trained from scratch.
Open source
Table understanding repo.
Synthetic data generation.
BhashaBench code.
Most downloaded.
Vision-language model.
Instruct model.
Multi-domain Indic benchmark.
Notable releases
Openness
Weights on Hugging Face.
People
- Ganesh RamakrishnanProfessor, IIT Bombay; leads BharatGen
Presented the first BharatGen models in October 2024.
Listed from the lab's own pages and public profiles.
Contact and community
bharatgen.com has a Contact us page.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



