MiniMax Speech 2.8 voice model
Original title:MiniMax Speech 2.8Audio Model
AI summary
MiniMax released its next-generation voice model MiniMax Speech 2.8, which uses native sound tag technology to simulate filler words such as "um" and "ah" and breathing pauses in human speech, significantly improving conversational naturalness. The model supports high-fidelity voice cloning from 10-second samples, accurately reproducing timbre and speaking rate while eliminating background noise and digital artifacts to output studio-grade clean audio. In addition, the model optimizes cross-language performance, starting with Mandarin-Japanese pairs to address accent bleed and achieve pronunciation closer to that of native speakers.
Key Takeaways
- MiniMax released its next-generation voice model MiniMax Speech 2.
- 8,which uses native sound tag technology to simulate filler words such as "um" and "ah" and…
- The model supports high-fidelity voice cloning from 10-second samples,accurately reproducing…
- In addition,the model optimizes cross-language performance,starting with Mandarin-Japanese pairs…
Quick Facts
- Published
- Updated
- Source
- MiniMax:Blog(网页)
- Category
- Other
10秒样本克隆真人声线,AI说话带'嗯啊'呼吸声,MiniMax语音模型上新
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 Speech 2.8 voice model. January 23, 2026. https://new.nat6.net/en/news/cmo4bnpds01noslk7v6054gq8/