option
Home
Flash News
Content
EdwardMoore
EdwardMoore
April 24, 2026

Xiaomi launches MiMo-V2.5 Full-Stack Speech Model Series, featuring three TTS models enabling emotion, tone, and voice control via natural language commands, and an open-source ASR model robust in noisy, multilingual environments. The models are available for free limited access and open-source to accelerate Agent ecosystem development.

Xiaomi launches MiMo-V2.5 Full-Stack Speech Model Series, featuring three TTS models enabling emotion, tone, and voice control via natural language commands, and an open-source ASR model robust in noisy, multilingual environments. The models are available for free limited access and open-source to accelerate Agent ecosystem development.
Comments (0)
0/300
OR