FireRedTeam open-sources FireRedTTS-2 long-conversation speech generation model
Original title:FireRedTeam/FireRedTTS2
AI summary
FireRedTeam released FireRedTTS-2, a streaming TTS system for long conversations aimed at podcasts and chatbots. It supports multilingual conversation generation of up to 3 minutes with 4 speakers, covering Chinese, English, Japanese, Korean, French, German, and Russian, and supports zero-shot cross-lingual voice cloning.
Key Takeaways
- FireRedTeam released FireRedTTS-2,a streaming TTS system for long conversations aimed at podcasts…
- It supports multilingual conversation generation of up to 3 minutes with 4 speakers,covering Chinese
- English,Japanese,Korean,French,German,and Russian,and supports zero-shot cross-lingual voice…
Quick Facts
- Published
- Updated
- Source
- FireRedTeam:原创语音与多模态项目
- Category
- Model Releases
- AI score
- 62
官方开源了长对话流式语音合成模型,给出多语言支持、延迟数据和部署方案,适合关注播客与对话生成的读者参考。
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: FireRedTeam open-sources FireRedTTS-2 long-conversation speech generation model. September 2, 2025. https://new.nat6.net/en/news/cmtyq8pub02uiroupmd6j0zeq/