Topic

#Voice

News, analysis and practical notes on Voice.

54articles

Articles on this topic

Newest first, page 1 of 6

ToolsJun 299 min

dots.tts is a next-generation open-source Text-to-Speech (TTS) model from RedNote, featuring a Fully Continuous architecture that completely …

ToolsJun 57 min

When AI is no longer just reading mechanically but can speak with laughter, pauses, and emotions, what will voice interaction look like? This …

ToolsMay 275 min

Explore the 8-billion-parameter MOSS-TTS-v1.5 speech synthesis model. Learn how this open-source tool uses precise pause control, 31-language …

ToolsMay 255 min

Looking for a high-naturalness speech synthesis solution? NetEase Youdao's Confucius4-TTS zero-shot voice cloning engine combines LLM …

ToolsApr 147 min

Explore the powerful potential of MOSS-TTS-Nano! This 0.1B parameter lightweight voice model focuses on deployment-first, supporting 20 languages …

ToolsApr 87 min

Want to create ultra-realistic AI voices at zero cost? This article provides a comprehensive analysis of VoxCPM2, an open-source TTS model …

ToolsApr 37 min

A new breakthrough in AI speech synthesis! The open-source OmniVoice model uses an innovative single-stage diffusion architecture to support over …

ToolsMar 317 min

Is traditional speech synthesis always distorted? Does finer compression really mean better generation quality? Take a look at Meituan's latest …

ToolsMar 274 min

Mistral AI introduces Voxtral TTS, featuring a 4B lightweight model, 70ms ultra-low latency, and 3-second voice cloning. This article provides a …

ToolsMar 115 min

Tired of stiff AI voices? Fish Audio S2 is now open source! Supporting 80+ languages with seamless multi-speaker switching and natural language …