📦

ASR — 语音识别技能

asr

AudioUtility

Unified ASR (Speech Recognition) skill with pluggable providers (strategy pattern). Supports: SiliconFlow (TeleAI/TeleSpeechASR). Use for transcribing audio/video files to text. Trigger: "转录", "识别语音", "语音转文字", "ASR", "transcribe", "语音识别". Auto-extracts audio from video files via ffmpeg.

Installation

npx skills add https://github.com/hwj123hwj/custom-skills --skill asr

Description

统一语音识别技能,基于策略模式,支持多个 ASR 后端切换。

Aliases

转录语音识别语音转文字ASR