Maya 2 Native: open-weight streaming speech in 12 languages
• 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
DheemanthReddy
updated 2
models 5 days ago
DheemanthReddy
published a
model 6 days ago
DheemanthReddy
published an article 10 days ago
Article
Maya 2 Native: open-weight streaming speech in 12 languages
maya-research
• • 1Tamil pronunciation is wrong in the landing page
1
#3 opened 12 days ago
by 
jenishngl
bharathkumarK
updated a
model 12 days ago
DheemanthReddy
posted an update 12 days ago
Post
114
Maya-2 voice model weights are officially live! 🇮🇳🇮🇳
The frontier voice model for India is now completely open-weight.
• Outperforms ElevenLabs v3, Sarvam Bulbul v3, and Cartesia Sonic 3.5
• 1.5B+ people covered across all 28 states and 8 union territories
• SOTA voice synthesis across 11 official languages
• 20 native speakers pre-loaded, ready out of the box
• Best-in-class zero-shot voice cloning
Built by a team of five from the land of languages.
Go build and have fun!
The frontier voice model for India is now completely open-weight.
• Outperforms ElevenLabs v3, Sarvam Bulbul v3, and Cartesia Sonic 3.5
• 1.5B+ people covered across all 28 states and 8 union territories
• SOTA voice synthesis across 11 official languages
• 20 native speakers pre-loaded, ready out of the box
• Best-in-class zero-shot voice cloning
Built by a team of five from the land of languages.
Go build and have fun!
bharathkumarK
published a
model 12 days ago
bharathkumarK
updated a
model 26 days ago
DheemanthReddy
updated a
model 28 days ago
DheemanthReddy
posted an update about 1 year ago
Post
571
We just announced our new model
Asking for your help with our announcement:
https://x.com/Dheemanthredy/status/1985790249080082607
Asking for your help with our announcement:
https://x.com/Dheemanthredy/status/1985790249080082607
DheemanthReddy
posted an update about 1 year ago
Post
1,370
We just released Maya-1-Voice, an open source voice AI model with voice design and emotions.
Describe voices in natural language. Add 20+ emotions like <laugh>, <cry>, <whisper> inline. 3B parameters, production-ready, runs on single GPU with vLLM.
Apache 2.0. Built on Llama backbone, predicts SNAC codec tokens for real-time streaming.
Model: https://huggingface.co/maya-research/maya-1-voice
Describe voices in natural language. Add 20+ emotions like <laugh>, <cry>, <whisper> inline. 3B parameters, production-ready, runs on single GPU with vLLM.
Apache 2.0. Built on Llama backbone, predicts SNAC codec tokens for real-time streaming.
Model: https://huggingface.co/maya-research/maya-1-voice
bharathkumarK
updated a
model about 1 year ago
DheemanthReddy
updated a
model about 1 year ago
Updated Code to run on Colab Notebook without Errors
#13 opened over 1 year ago
by 
theshresthshukla
Local Installation Video and Testing - Step by Step
1
#8 opened over 1 year ago
by 
fahdmirzac
how many voices dose this model has
2
#7 opened over 1 year ago
by 
oyy-jainil
Voice Cloning with Veena
1
#6 opened over 1 year ago
by 
Aaryan39
How many hours of speech data was this model trained on?
➕ 1
2
#3 opened over 1 year ago
by 
stefanr123
Taking 50 sec for me on Colab
8
#15 opened over 1 year ago
by 
banank1989