All models
lightweight

NeuTTS Air

Apache-2.0

On-device-class TTS with instant cloning from ~3 seconds

NeuTTS Air from Neuphonic is built to run in real time on a CPU — a ~0.7B-parameter model on a Qwen backbone that still manages instant voice cloning from around three seconds of reference audio. It's designed for on-device privacy, which also makes it one of the cheapest modern TTS models to serve.

Voices

1 voice
Neutral
Reference-baseddefault
—
NeutralEmotionalNumbers & Dates

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

git clone https://github.com/neuphonic/neutts-air

NeuTTS Air FAQ

Do I need a GPU to run NeuTTS Air?

No — NeuTTS Air runs in real time on a CPU, no GPU required. It's one of the few open TTS models that does.

Can NeuTTS Air clone voices?

Yes — NeuTTS Air supports voice cloning from reference audio.

What license is NeuTTS Air released under?

NeuTTS Air is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does NeuTTS Air support?

NeuTTS Air supports English.

Is there a hosted NeuTTS Air API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to NeuTTS Air and every other model in this directory. No CUDA, Docker, or GPU needed.