AI Agent Skills

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

On-device wake word detection powered by deep learning

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows,…