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
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.
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/