MiMo-V2.5 Voice

Bilingual ASR for dialects, code-switching, and songs

111 followers

Bilingual ASR for dialects, code-switching, and songs

111 followers

Visit website

Transcription

•

AI Voice Agent Infrastructure

MiMo-V2.5-ASR is an 8B open-source speech recognition model from Xiaomi that transcribes Mandarin, English, eight Chinese dialects, code-switched speech, and song lyrics. Built for ML engineers, researchers, and developers building real-world voice applications.

MiMo-V2.5 Voice Alternatives

Looking beyond MiMo-V2.5 Voice? Try ElevenLabs, Deepgram, AssemblyAI, Vapi, and Cartesia Sonic. Deepgram and AssemblyAI excel at real-time ASR and diarization; ElevenLabs and Cartesia Sonic shine for ultra-natural, fast TTS; Vapi speeds up voice agent development—great for multilingual and code-switching needs.