OpenMOSS open-sources MOSS-TTSD-V0 bilingual Chinese-English conversational speech generation model
Original title:MOSS-TTSD: 文本到口语对话生成
AI summary
OpenMOSS released and open-sourced MOSS-TTSD-V0, supporting bilingual Chinese-English conversational speech generation, zero-shot two-speaker voice cloning, sound event control, and long speech generation. Model weights, inference code, and API are all open-source and available for commercial use.
Key Takeaways
- OpenMOSS released and open-sourced MOSS-TTSD-V0,supporting bilingual Chinese-English…
- zero-shot two-speaker voice cloning,sound event control,and long speech generation.
- Model weights,inference code,and API are all open-source and available for commercial use.
Quick Facts
- Published
- Updated
- Category
- Model Releases
- AI score
- 69
原文给出训练数据规模、Codec 设计和对比结果,读者可据此评估这个开源对话语音模型的可复用价值。
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: OpenMOSS open-sources MOSS-TTSD-V0 bilingual Chinese-English conversational speech generation model. June 20, 2025. https://new.nat6.net/en/news/cmtyo3imp03ldrog0za18eo67/