README
🐢
AI & ML interests
None defined yet.
Recent Activity
View all activity
DheemanthReddy
updated a
Space 13 days ago
Taking 50 sec for me on Colab
8
#15 opened 10 months ago
by 
banank1989
Reference Audio
3
#32 opened 6 months ago
by 
JoshJarabek
The important question
👍 4
8
#4 opened 6 months ago
by 
yukiarimo
[FLAW] Model cannot pronounciate seperate characters correctly
4
#26 opened 6 months ago
by 
simzhou
The important question
👍 4
8
#4 opened 6 months ago
by yukiarimo
[Bug?] The generated wav reads description transcript as well...
8
#25 opened 6 months ago
by simzhou
audio quality is weird
2
#29 opened 6 months ago
by 
AnusreeDas01
Remove the preset override.
❤️ 1
1
#2 opened 6 months ago
by 
Gapeleon
Is it coming for Hindi + English Language?
1
#27 opened 6 months ago
by 
bhavkaabhav
[FLAW] Model cannot pronounciate seperate characters correctly
4
#26 opened 6 months ago
by simzhou
[Bug?] The generated wav reads description transcript as well...
8
#25 opened 6 months ago
by simzhou
Indian Voices?
9
#7 opened 6 months ago
by 
weightsnweights
ComfyUI Node
3
#3 opened 6 months ago
by 
anujkk
[ISSUE] Transformers inference script doesn't work.
👀👍 3
8
#2 opened 6 months ago
by 
CCRss
audio quality is weird
2
#29 opened 6 months ago
by AnusreeDas01
I made maya1 faster and output 48khz audio instead of 24khz
🔥 3
7
#30 opened 6 months ago
by 
YatharthS
Maya1 Voice Model is now available to try on Fal
🔥 2
2
#31 opened 6 months ago
by 
DheemanthReddy
DheemanthReddy
posted an update 6 months ago
Post
449
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 7 months ago
Post
1242
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