NeuTTS Nano is a speech foundation model, 3x smaller than NeuTTS Air, that runs on CPU in real-time, with instant voice cloning.
AI & ML interests
TTS, Audio Codecs
Recent Activity
Organization Card
Neuphonic builds ultra-realistic, on-device voice AI that brings speech to life with human-like quality.
Our speech foundation models run locally - private, secure, and lightning-fast - without the need for GPUs or cloud dependence. From instant voice cloning to low-latency text-to-speech, Neuphonic enables enterprises and developers to integrate natural, responsive conversations anywhere: online or offline, on devices or at the edge.
Backed by leading global investors, we’re creating a future where engaging with AI is seamless, private, and effortless.
models
11
neuphonic/neutts-nano-q4-gguf
Text-to-Speech
•
0.3B
•
Updated
•
607
•
7
neuphonic/neutts-nano-q8-gguf
Text-to-Speech
•
0.3B
•
Updated
•
555
•
4
neuphonic/neutts-nano
Text-to-Speech
•
0.3B
•
Updated
•
214
•
21
neuphonic/neutts-air-q4-gguf
Text-to-Speech
•
0.7B
•
Updated
•
3.72k
•
42
neuphonic/neutts-air-q8-gguf
Text-to-Speech
•
0.7B
•
Updated
•
1.86k
•
33
neuphonic/neutts-air
Text-to-Speech
•
0.7B
•
Updated
•
18.7k
•
835
neuphonic/neucodec-onnx-decoder
Audio-to-Audio
•
Updated
•
4.14k
•
11
neuphonic/neucodec-onnx-decoder-int8
Updated
•
358
•
2
neuphonic/neutts-air-onnx
Updated
•
2
neuphonic/distill-neucodec
Audio-to-Audio
•
Updated
•
4.56k
•
16