小米 MiMo-Audio

Xiaomi's speech understanding/generation model — few-shot learning, emergent abilities

★ pending verification stars, verified 2026-09-30Category: AI Voice / TTS / ASR

No direct GitHub link yet — star count pending verification before we write it up.

Xiaomi's speech understanding and generation model with few-shot learning and emergent abilities.

Voice AI: lifelike TTS, accurate ASR, and real-time voice agents.

Similar open-source projects

Dia

★ 19,393

Ultra-realistic conversational TTS from Nari Labs — multi-speaker dialogue in one pass

AI Voice / TTS / ASRGitHub ↗

TEN-Agent

★ 11,144

Open-source real-time voice-interaction agent platform — the "agent framework" for voice

AI Voice / TTS / ASRGitHub ↗