AI Agent Skills

On-device wake word detection powered by deep learning

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

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

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

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iO…

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen…

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