Local Whisper (cpp)

该 Skill 提供包装脚本 scripts/whisper-local.sh，调用本机 whisper-cli 与 large-v3-turbo 模型，对音频文件做离线语音转写（-l auto -nt，输出无时间戳文本）。模型需按 Setup 用 wget 从 Hugging Face 下载到 /usr/share/whisper.cpp-model-large-v3-turbo/。

wuxxin

热度 93.36

最近更新 2026-05-11 17:25:56

分类：效率依赖：代码执行 / 读写文件应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add local-whisper-cpp

Metadata

name: local-whisper-cpp
description: Local speech-to-text using whisper-cli (whisper.cpp).
metadata: {"openclaw":{"emoji":"🌬️","requires":{"bins":["whisper-cli"]}}}

Local Whisper (cpp)

Transcribe audio files locally using whisper-cli and the large-v3-turbo model.

Usage

You can use the wrapper script:

scripts/whisper-local.sh <audio-file>

Or call the binary directly:

whisper-cli -m /usr/share/whisper.cpp-model-large-v3-turbo/ggml-large-v3-turbo.bin -f <file> -l auto -nt

Scripts

Location: scripts/whisper-local.sh (inside skill folder)
Model: /usr/share/whisper.cpp-model-large-v3-turbo/ggml-large-v3-turbo.bin
GPU: Enabled via whisper-cli.

Setup

Download the model to /usr/share/whisper.cpp-model-large-v3-turbo/:

wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin?download=true -O /usr/share/whisper.cpp-model-large-v3-turbo/ggml-large-v3-turbo.bin