Features
Transcribes Mandarin and English
Supports eight Chinese dialects
Handles code-switched speech
Transcribes song lyrics in mixed vocal/instrumental scenarios
Robust in strong noise, far-field, and multi-speaker conditions
Accurate recognition of knowledge-dense content
Open-source 8B parameter model
Priced at ¥0.5 per hour of audio input
Part of MiMo-V2.5 series (V2 deprecated as of June 30, 2026)
API access via OpenAI/Anthropic compatible endpoints
No real-time streaming (latency not specified)
Does not support speaker diarization
Does not support emotion recognition
Model weights available for self-hosting
Supports audio input only (no text/image generation)
Open-source framework for voice/video/robotics agents
Inference gateway for TTS, LLM, STT models
Turn Detector v1.0 for accurate end-of-turn detection
C++ SDK for low-latency agents
Embed voice agents on any website
Outbound phone agent voicemail/IVR detection
Multi-language SDKs (Python, Node.js, C++)
Phone numbers and SIP telephony integration
Full-stack observability per session
Agent Console for real-time debugging
LiveKit Portal for robotic teleoperation and data collection
Global edge network for low-latency streaming
