NeuTTS-2E is a super-fast, highly realistic TTS model with rich emotional control - happy, sad, angry, disgusted, surprised, fearful, and neutral!
AI & ML interests
Speech foundation models that run locally - private, secure, and with low-latency - without the need for GPUs or cloud dependence.
Recent Activity
NeuTTS Nano is a TTS model, 3x smaller than NeuTTS Air, that runs on CPU in real-time - now in English, Spanish, French, and German versions!
-
NeuTTS-Nano Multilingual Collection
🌍47Generate speech with voice cloning, now in four languages!
-
neuphonic/neutts-nano
Text-to-Speech • 0.2B • Updated • 3.37k • 73 -
neuphonic/neutts-nano-q8-gguf
Text-to-Speech • 0.2B • Updated • 323 • 24 -
neuphonic/neutts-nano-q4-gguf
Text-to-Speech • 0.2B • Updated • 2.1k • 17
We introduce NeuCodec, a 0.8kbps audio codec that outputs audio at 24kHz.
NeuTTS-2E is a super-fast, highly realistic TTS model with rich emotional control - happy, sad, angry, disgusted, surprised, fearful, and neutral!
NeuTTS Nano is a TTS model, 3x smaller than NeuTTS Air, that runs on CPU in real-time - now in English, Spanish, French, and German versions!
-
NeuTTS-Nano Multilingual Collection
🌍47Generate speech with voice cloning, now in four languages!
-
neuphonic/neutts-nano
Text-to-Speech • 0.2B • Updated • 3.37k • 73 -
neuphonic/neutts-nano-q8-gguf
Text-to-Speech • 0.2B • Updated • 323 • 24 -
neuphonic/neutts-nano-q4-gguf
Text-to-Speech • 0.2B • Updated • 2.1k • 17
NeuTTS Air is a speech foundation model that runs on CPU in real-time, with instant voice cloning.
We introduce NeuCodec, a 0.8kbps audio codec that outputs audio at 24kHz.