Topic
News, analysis and practical notes on Voice.
Explore Aratako's latest MioTTS project, a series of ultra-lightweight TTS models based on LLM architecture. From the extreme 0.1B version to …
Breaking the black box of voice models! We dissect KaniTTS2, a 350M parameter model based on the LFM2 architecture that solves long-form speech …
MOSS-TTS is now open-source! This production-grade AI audio solution features 5 core models, supporting zero-shot voice cloning and long dialogue …
The Qwen team has officially open-sourced the Qwen3-TTS series models. This solution, known as the "Full Suite," provides complete functions from …
Soprano TTS has released the training code Soprano-Factory and encoder. This ultra-lightweight model supports 15ms low-latency streaming and now …
The open-source audio super-resolution model NovaSR, weighing only 52KB, is shaking up the community! This article dives into how NovaSR achieves …
In an environment where AI applications are becoming increasingly popular, developers and enterprises are always looking for more efficient …
Do you want human-like AI voice but are limited by hardware or generation speed? MiraTTS has emerged, an LLM-based speech synthesis model that …
Voice AI technology is finally no longer held hostage by expensive APIs and network latency. NeuTTS Air, launched by Neuphonic, is a lightweight …
Alibaba Cloud's FunAudioLLM team has released CosyVoice 3, a TTS model with only 0.5B parameters that supports 9 languages including Chinese, …
© 2026 Communeify. All rights reserved.
