FunASR Review — Self-Hosted AI Tool
Our review of FunASR — features, strengths, and trade-offs.
FunASR is an open-source, end-to-end speech recognition toolkit by ModelScope that supports training, inference, and deployment of ASR models including streaming ASR, voice activity detection (VAD), punctuation restoration, speaker diarization, and emotion recognition. It provides OpenAI-compatible and MCP APIs for easy integration.