speech synthesis

NeuTTS Air

Small on-device text-to-speech model with voice cloning, paired with the NeuCodec audio codec.

Neuphonic

Levelmodel

Classspeech synthesis

Parameters747.93M

Contextnot in the notes

Released15 Sep 2025

Opennessopen weights permissive

Runs onlaptop, mobile or NPU

Statusactive

R&D Topics

Large-scale zero-shot text-to-speechproduced by On-device text-to-speechexemplar

Identity

Developer: Neuphonic
Family: not in the notes
Released: 15 Sep 2025 sourcesregistry date
Weights published: –
Record checked: 12 Oct 2026

Where this comes from

Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture: other
Total parameters: 747.93M sources
Active parameters: –
Checkpoint parameters: –
Context length: not in the notes
Input: text, audio
Output: audio

Where this comes from

Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness: open weights permissive
Licence: Apache License 2.0 sources
Access routes: open weights download

Where this comes from

The licence file governs over registry tags and aggregator labels.

Deployment

Runs on: laptop, mobile or NPU
Footprint: not in the notes
Runtimes: not in the notes

Where this comes from

Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support: not stated
Regional languages: not in the notes
Jakarta hosting: unknown
Languages: not in the notes

Where this comes from

Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Links

Developer

Neuphonicstartup

Model

NeuTTS AirNeuphonic, speech synthesis

R&D TopicsLarge-Scale Zero-Shot Text-to-Speech On-Device Text-to-Speech

Use Casesnone recorded

Who Runs Itnone recorded

Graph

Organisations 1

NeuphonicstartupDeveloper

R&D topics 2

Large-Scale Zero-Shot Text-to-SpeechText-to-speech trained on tens of thousands of hours that speaks in an unseen voice from…produced byOn-Device Text-to-SpeechSmall text-to-speech models that run offline on phones, CPUs or microcontrollers without…exemplar

Sources

huggingface.co/neuphonic/neutts-air https://huggingface.co/neuphonic/neutts-air

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "NeuTTS Air", https://aurion.semai.id/models/neuphonic-neutts-air/, records of October 2026.