Model reference · open weights

neutts-air

Audio neuphonic Text→speech 1 build Open weights 4k dl/mo

neutts-air is an open-weight audio or speech model from neuphonic. neutts-air (BF16) weighs 1.5 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • NeuTTS Air is a text-to-speech model developed by Neuphonic that features instant voice cloning and is optimized for on-device deployment.
  • The model contains 748M parameters and is built on a Qwen 0.5B backbone, allowing for real-time generation on mid-range devices.
  • It is distributed under the Apache 2.0 license and available in GGML format for efficient inference.

Summary of the neuphonic/neutts-air model card, 2026-10-01

What it is

Released byneuphonic
Released2025-09-15
Parameters748M
VRAM1.5 GB for the weights

What it runs on

Memory and cards for neutts-air (BF16)

1.5 GBweights, file size
1.6 GBruntime overhead
CardOne streamMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms