Model Releases

FunAudioLLM releases Fun-CosyVoice 3.0 open-source speech synthesis model

Original title:QwenAudio/CosyVoice

AI summary

Alibaba Tongyi's FunAudioLLM team open-sourced Fun-CosyVoice 3.0, an LLM-based TTS system. The team says it surpasses the previous CosyVoice 2.0 in content consistency, speaker similarity, and prosodic naturalness, and targets zero-shot multilingual speech synthesis.

Key Takeaways

  • Alibaba Tongyi's FunAudioLLM team open-sourced Fun-CosyVoice 3.
  • 0,an LLM-based TTS system.
  • The team says it surpasses the previous CosyVoice 2.
  • 0 in content consistency,speaker similarity,and prosodic naturalness,and targets zero-shot…

Quick Facts

Published
Updated
Source
通义 QwenAudio:原创语音项目
Category
Model Releases
AI score
62
Read the original Read the full article at the original source
Why it matters

官方发布开源 TTS 新版本,附评测表、安装与部署方式,适合关注多语言语音合成落地的开发者参考。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: FunAudioLLM releases Fun-CosyVoice 3.0 open-source speech synthesis model. July 3, 2024. https://new.nat6.net/en/news/cmtyq8s6102v2rouphfy2z5xw/

View all →