← 返回 Skills 市场
251
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install meeting-to-text
功能描述
Create a fully local speaker-separated .txt transcript from a meeting recording, meeting screen recording, speech audio, or local video/audio file. Use this...
安全使用建议
This skill will execute the bundled Python script on your machine and expects local models, a 3D-Speaker repo, and ffmpeg; if those are absent it will try to download a speaker model from ModelScope at runtime (so it is not strictly offline). Before installing/running: (1) review the script and decide whether you trust running arbitrary Python code and subprocesses on your system; (2) prepare the local directories listed in references/runtime_paths.md (or set the MEETING_TO_TEXT_* env vars) to avoid runtime downloads; (3) ensure ffmpeg is available at the expected path or set MEETING_TO_TEXT_FFMPEG; (4) run the skill inside an isolated/temporary environment if you want to limit risk. If you require guaranteed offline behavior, do not use this skill unless you pre-populate the expected model cache and repo paths.
功能分析
Type: OpenClaw Skill
Name: meeting-to-text
Version: 1.0.0
The skill bundle provides a legitimate local workflow for transcribing audio and video files with speaker diarization. The Python script (meeting_to_text.py) utilizes standard machine learning libraries such as FunASR and Torch, and interacts with FFmpeg via safe subprocess calls to normalize media. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the network activity is limited to downloading model weights from a legitimate repository (ModelScope) if they are not already present locally.
能力评估
Purpose & Capability
Name/description: local speaker-separated transcript. Implementation: expects local ASR/VAD model directories and a local 3D-Speaker repo, which is coherent. However the script also calls modelscope.hub.snapshot_download to fetch a speaker model at runtime if not cached — this contradicts the 'fully local' claim. The skill declares no required env vars or binaries, yet it requires a local ffmpeg executable and several model/repo paths to be present (or network access to download a model).
Instruction Scope
SKILL.md instructs running the bundled Python entrypoint and to read runtime_paths.md, and treats the last stdout line as JSON — that matches the script. It does not disclose that the script may perform a network download (modelscope.snapshot_download) if a speaker model cache is missing, nor does it highlight the strong dependency on a local 3D-Speaker repo layout and local models; this is scope-opaque and could surprise users who expect strictly offline operation.
Install Mechanism
No install spec (instruction-only + bundled Python script), so nothing is written by an installer. However, the runtime script will import libraries and call snapshot_download at runtime (network download) and invoke ffmpeg via subprocess; there is no package install step described.
Credentials
Requires no credentials or special env vars in metadata, which is appropriate. The code does rely on several local path defaults (PROJECT_ROOT-based) and allows overrides via MEETING_TO_TEXT_* env vars — these are reasonable but not declared. No secrets are requested, but the skill reads and writes local files (models, repos, temp dirs) and may download model artifacts from ModelScope.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges. It executes as a one-off script and does not modify other skills or global agent config.
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 meeting-to-text - 安装完成后，直接呼叫该 Skill 的名称或使用
/meeting-to-text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
v1.0.0
Initial release of the meeting-to-text skill:
- Converts local meeting recordings (audio/video) into fully local, speaker-separated plain text transcripts.
- Supports a variety of common audio and video file types as input.
- Outputs transcripts with timestamps and default speaker labels like 说话人1, 说话人2, etc.
- Uses local ASR and speaker diarization models; no cloud processing.
- Clearly reports transcript location, speaker count, and any warnings or errors.
元数据
常见问题
meeting-to-text 是什么？
Create a fully local speaker-separated .txt transcript from a meeting recording, meeting screen recording, speech audio, or local video/audio file. Use this... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 251 次。
如何安装 meeting-to-text？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install meeting-to-text」即可一键安装，无需额外配置。
meeting-to-text 是免费的吗？
是的，meeting-to-text 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
meeting-to-text 支持哪些平台？
meeting-to-text 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 meeting-to-text？
由 henrCh1（@henrch1）开发并维护，当前版本 v1.0.0。
推荐 Skills