MiniMax releases next-generation speech model Speech 2.6
Original title:MiniMax Speech 2.6Audio Model
AI summary
MiniMax released the speech model Speech 2.6, cutting end-to-end latency to under 250 milliseconds and supporting real-time conversation. It adds multilingual parsing of special formats, automatically reading out URLs, emails, phone numbers, dates and amounts without preprocessing. A new Fluent LoRA feature preserves timbre and generates fluent speech even when source recordings carry accents, supporting more than 40 languages. It has been adopted by platforms such as LiveKit and Vapi as well as smart hardware.
Key Takeaways
- MiniMax released the speech model Speech 2.
- 6,cutting end-to-end latency to under 250 milliseconds and supporting real-time conversation.
- It adds multilingual parsing of special formats,automatically reading out URLs,emails,phone…
- A new Fluent LoRA feature preserves timbre and generates fluent speech even when source recordings…
- It has been adopted by platforms such as LiveKit and Vapi as well as smart hardware.
Quick Facts
- Published
- Updated
- Source
- MiniMax:Blog(网页)
- Category
- Other
MiniMax发布Speech 2.6语音模型,支持Voice Agent场景,实现超低延迟与Fluent LoRA语音克隆优化。
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: MiniMax releases next-generation speech model Speech 2.6. October 30, 2025. https://new.nat6.net/en/news/cmnw1zatl027bslc3y6bgjvnw/