Neuphonic Releases NeuTTS Air for On-Device AI Speech
The new Apache 2.0 text-to-speech model is built on a Qwen2 architecture and optimized for local inference with GGUF support.
A new open-source text-to-speech (TTS) model called NeuTTS Air has been released by developer Neuphonic. Designed for on-device applications, the model features voice cloning capabilities, allowing users to generate speech in a target voice from just a short audio sample.
Uniquely, NeuTTS Air is built upon a Qwen2 language model architecture, a different approach from many specialized TTS systems. The release includes GGUF-quantized versions, making it compatible with popular local inference frameworks like llama.cpp and accessible on a wide range of consumer hardware without requiring a powerful GPU.
The combination of local execution, voice cloning, and a permissive Apache 2.0 license makes NeuTTS Air a significant new tool for developers. It opens up possibilities for building private-by-design applications, from custom voice assistants to dynamic content creation, without relying on cloud-based APIs and their associated costs and privacy concerns.
Developers can explore the model, listen to audio samples, and download the weights from the project's Hugging Face repository.
Sources
- Visit
neuphonic/neutts-air
Hugging Face
0 comments
No comments yet. Be the first to weigh in.
More in Text → Speech
Zyphra Releases Open-Source Zonos 2 TTS Model
The new text-to-speech model offers a commercially permissive alternative for developers in a field still dominated by closed-source APIs.
Boson AI's Higgs Audio v3 Offers Expressive, Multilingual TTS
The new 4-billion-parameter text-to-speech model is available for non-commercial use, promising fine-grained control over vocal delivery.
MOSS-TTS Aims for More Robust Speech Synthesis
A new text-to-speech model introduces 'delay-pattern decoding' to solve common word skipping and repetition errors in parallel generation.