neutts-air-de-preview

jaeyong2/neutts-air-de-preview

neutts-air-de-preview is a text-to-speech model from jaeyong2. Use it when you need text read aloud. It is set up for transformers. The card lists the license as apache-2.0.

<audio controls <source src="https://huggingface.co/jaeyong2/neutts-air-de-preview/resolve/main/train000.wav" type="audio/wav" </audio

Downloads · 30 days

13% of all-time downloads

All-time downloads

434

Public

Parameters

553M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 96%

At a glance

Task: Text-to-Speech
Library: transformers
License: apache-2.0
Model type: qwen2
Access: Public
Created: Nov 5, 2025
Updated: Nov 29, 2025
SHA: da6b2192

Base models

neuphonic/neutts-air

Model card

From the Hugging Face model README

Install info

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

Example

from neuttsair.neutts import NeuTTSAir
import soundfile as sf

tts = NeuTTSAir(backbone_repo="jaeyong2/neutts-air-de-preview", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu")
input_text = "Denn so sehr hat Gott die Welt geliebt, dass er seinen einzigen Sohn gab, damit jeder, der an ihn glaubt, nicht verloren geht, sondern ewiges Leben hat."

ref_text = "train_000.txt"
ref_audio_path = "train_000.wav"

ref_text = open(ref_text, "r").read().strip()
ref_codes = tts.encode_reference(ref_audio_path)

wav = tts.infer(input_text, ref_codes, ref_text)
sf.write("new.wav", wav, 24000)

ref_audio (SinclairSchneider/german_voice_cb)

jaeyong2/neutts-air-de result

neuphonic/neutts-air result

License

neuphonic/neutts-air : https://choosealicense.com/licenses/apache-2.0/

Acknowledgement

This research is supported by TPU Research Cloud program.

Task: Text-to-Speech
Library: transformers
Type: qwen2
License: apache-2.0
Languages: de, en
Created: Nov 5, 2025
Updated: Nov 29, 2025