Local TTS model
NeuTTS Air
First super-realistic TTS LLM that runs in real-time on CPU. 748M params, LLaMA 3.2 backbone + NeuCodec audio tokenizer. GGUF-native - perfect for on-device agents and offline apps. Instant 3s voice cloning.
Edge ready
text-to-speech generation
1 languages
Apache 2.0
Quality
9/10
Speed
9.5/10
Model size
0.75 GB
Voices
Zero-shot cloning (3s reference)
Can NeuTTS Air run locally?
NeuTTS Air can generate speech locally for private voice workflows. Start with pip install neutts.
Apache 2.0 license. Still verify upstream usage notes before shipping.
pip install neutts
Upstream source
cloningrealtimestreaminglow-latency
Audio profile
Best fit
NeuTTS Air is best for local voice cloning and expressive speech generation.
Hardware: cpugpuappleedge
Model details
Type
Local TTS model
Family
neutts
Latency
ultra-low
Formats
ggufonnxpytorch
Languages
en
Context
LLaMA 3.2 backbone + NeuCodec, CPU real-time
Install locally
01
Check runtimeConfirm the backend supports gguf, onnx, pytorch on your machine.02
Install modelUse the upstream command or repository instructions.03
Test locallyRun a short private audio prompt before moving into production workflows.pip install neutts
Good for
- text-to-speech generation
- Edge ready local workflows
- cloning, realtime, streaming
Watch before shipping
- Validate pronunciation, latency and artifacts with your own voice samples.
- Review the upstream license and acceptable-use notes.
- Benchmark on your target CPU, Apple Silicon or GPU setup.
Related TTS and speech models
OpenMOSS / MOSI.AI
MOSS-TTS-Nano
Local TTS model · Q 8.5 · Speed 9.7
hexgrad
Kokoro TTS
Local TTS model · Q 9.2 · Speed 9.8
Speech Research (SWivid)
F5-TTS v1.1
Local TTS model · Q 9.5 · Speed 9.2
Speech Research
F5-TTS
Local TTS model · Q 9.4 · Speed 9
Amphion Team
MaskGCT
Local TTS model · Q 9.4 · Speed 9
Zyphra
Zonos v0.1
Local TTS model · Q 9.5 · Speed 8.5
Kyutai
Moshi
Local TTS model · Q 9 · Speed 9.5
Alibaba FunAudioLLM
CosyVoice 2
Local TTS model · Q 9.3 · Speed 8.8