← 返回 Skills 市场
522
总下载
0
收藏
3
当前安装
3
版本数
在 OpenClaw 中安装
/install whisper-cpp
功能描述
Install and use whisper.cpp (local, free/offline speech-to-text) with OpenClaw. Supports downloading different ggml model sizes (tiny/base/small/medium/large...
安全使用建议
This skill appears to do what it says: build whisper.cpp locally, download ggml models from Hugging Face, install a wrapper into ~/.local, and configure OpenClaw to call that wrapper for inbound audio. Before installing: (1) ensure you have build tools, ffmpeg, and enough disk space (models can be large); (2) review and back up your OpenClaw config because scripts will patch it and restart the gateway; (3) note the wrapper currently only accepts models 'base' or 'small' despite documentation mentioning larger models — if you plan to use medium/large, inspect/adjust bin/openclaw-whisper-stt.sh; (4) verify you trust the upstream GitHub and Hugging Face sources; (5) run the install commands interactively (not as root) and inspect what they do if you have security concerns. Overall the skill is coherent and proportional to its purpose.
功能分析
Type: OpenClaw Skill
Name: whisper-cpp
Version: 1.0.2
This skill bundle is designed to install and configure local whisper.cpp for speech-to-text within OpenClaw. All scripts (install_whisper_cpp.sh, download_models.sh, install_wrapper.sh, patch_openclaw_audio.sh, cleanup_build.sh) perform actions directly related to this purpose, such as cloning the official whisper.cpp repository, compiling it, downloading models from Hugging Face, installing binaries to user-local directories (~/.local/bin, ~/.local/lib), and configuring OpenClaw via its CLI. The `bin/openclaw-whisper-stt.sh` wrapper script correctly quotes input paths when calling `ffmpeg` and `whisper-cli`, mitigating potential command injection vulnerabilities. The SKILL.md instructions are clear and do not contain any prompt injection attempts to manipulate the agent into malicious or hidden actions. No evidence of data exfiltration, unauthorized network activity, persistence mechanisms, or obfuscation was found.
能力评估
Purpose & Capability
The name/description (local whisper.cpp STT for OpenClaw) aligns with the scripts: they build whisper.cpp from the upstream GitHub repo, download ggml model binaries from Hugging Face, install a wrapper into ~/.local/bin, and patch OpenClaw to call the wrapper for inbound audio. One inconsistency: SKILL.md and download_models.sh advertise many model sizes (tiny/base/small/medium/large-*) but the runtime wrapper (bin/openclaw-whisper-stt.sh) enforces MODEL_NAME to be only 'base' or 'small'. This is a capability mismatch (documentation vs runtime).
Instruction Scope
The SKILL.md installation steps are explicit and limited to building whisper.cpp, downloading models into ~/.cache/whisper, installing the wrapper into ~/.local/bin, patching OpenClaw's tools.media.audio config, and restarting the gateway. The scripts operate on user-home directories (~/.local, ~/.cache) and do not attempt to read unrelated system files or export secrets. The patch script will restart the gateway (impactful), which is within the skill's stated goal but is a behavior the user should expect.
Install Mechanism
There is no packaged install spec; the provided scripts clone the known upstream repo (https://github.com/ggerganov/whisper.cpp) and download model binaries from Hugging Face (huggingface.co/ggerganov/whisper.cpp). Those are well-known sources. The build process compiles locally with cmake and installs artifacts under the user's home. This is expected for a local build; the main risk is the usual build-time exposure and disk usage for large models.
Credentials
The skill requests no credentials or secret environment variables. Runtime uses ordinary env items (HOME, optional OPENCLAW_WHISPER_MODEL and OPENCLAW_WHISPER_LANG) and checks for required tools (git, cmake, ffmpeg, curl). No unrelated service tokens or privileged system credentials are requested.
Persistence & Privilege
The skill installs a wrapper symlink into ~/.local/bin, places libs in ~/.local/lib, stores models in ~/.cache/whisper, and PATCHES OpenClaw configuration and restarts the gateway to enable local STT. It does not set always:true, but it does modify OpenClaw's config persistently — users should be aware this changes their gateway behavior until reverted.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install whisper-cpp - 安装完成后，直接呼叫该 Skill 的名称或使用
/whisper-cpp触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
- Added automated install and management scripts: `install_whisper_cpp.sh`, `download_models.sh`, `install_wrapper.sh`, and `cleanup_build.sh`.
- Introduced a dedicated wrapper executable: `openclaw-whisper-stt` for consistent local STT.
- Expanded model support: now supports all ggml model sizes (`tiny`, `base`, `small`, `medium`, `large-v*`).
- Improved documentation: simplified setup and configuration steps, clarified model and language selection.
- Removed extraneous legacy notes file.
v1.0.1
- Added instructions to copy whisper.cpp shared libraries to `~/.local/lib` and update `LD_LIBRARY_PATH` to ensure CLI works independently of the build directory.
- Updated wrapper script to support selecting language via the `OPENCLAW_WHISPER_LANG` environment variable, with auto-detection as the default.
- Improved cleanup steps to recommend deleting both build directory and repository for disk space saving.
- Clarified usage instructions for language selection and shared library handling in the documentation.
v1.0.0
- Initial release of whisper-cpp skill for OpenClaw.
- Provides local, offline speech-to-text using whisper.cpp without paid APIs.
- Includes build and setup instructions, model downloads, and a CLI wrapper for easy integration.
- Supports decoding various audio formats (OGG, Opus, MP3, WAV) and flexible model selection (base, small).
- Adds patch script for quick integration with OpenClaw’s audio transcription pipeline.
元数据
常见问题
Local Whisper 是什么？
Install and use whisper.cpp (local, free/offline speech-to-text) with OpenClaw. Supports downloading different ggml model sizes (tiny/base/small/medium/large... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 522 次。
如何安装 Local Whisper？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install whisper-cpp」即可一键安装，无需额外配置。
Local Whisper 是免费的吗？
是的，Local Whisper 完全免费（开源免费），可自由下载、安装和使用。
Local Whisper 支持哪些平台？
Local Whisper 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Local Whisper？
由 TrueNight（@truenight）开发并维护，当前版本 v1.0.2。
推荐 Skills