← 返回 Skills 市场
Video To Text Transcription Free
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
61
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-to-text-transcription-free
功能描述
Get text transcripts ready to post, without touching a single slider. Upload your video files (MP4, MOV, AVI, WebM, up to 500MB), say something like "transcr...
安全使用建议
This skill appears to do what it says: it uploads video files and uses a NEMO_TOKEN to call nemovideo's API for transcription and rendering. Before installing or using it: (1) Confirm you trust the external domain (mega-api-prod.nemovideo.ai) — your videos will be uploaded there; (2) Prefer letting the skill generate an anonymous token rather than entering a personal account token, since providing your NEMO_TOKEN may give it full access to your account; (3) Ask the publisher to clarify the configPath discrepancy (SKILL.md lists ~/.config/nemovideo/ while registry metadata did not) if you are concerned about local config reads; (4) Test with non-sensitive videos first and review the service's privacy/terms if you plan to process private data.
功能分析
Type: OpenClaw Skill
Name: video-to-text-transcription-free
Version: 1.0.0
The skill is a functional wrapper for a video transcription service hosted at mega-api-prod.nemovideo.ai. It implements standard API interactions including anonymous token generation, session management, and file uploads. The instructions in SKILL.md are well-defined, providing clear logic for the AI agent to map user intents to specific API endpoints without any evidence of malicious data exfiltration, unauthorized local execution, or harmful prompt injection.
能力评估
Purpose & Capability
The name/description describe cloud video transcription and the SKILL.md instructs the agent to obtain a token, create a session, upload video files, request transcriptions/rendering, and download outputs — all coherent with the claimed purpose. Requesting a NEMO_TOKEN is appropriate for an API-driven service.
Instruction Scope
Instructions require network calls to https://mega-api-prod.nemovideo.ai for auth, uploads, SSE and rendering; they explicitly instruct uploading user video files (or URLs) and storing session_id. This is expected for a cloud transcription service, but it does mean user content will be transmitted to a third party. The SKILL.md also references auto-detecting platform from an install path and a config path (~/.config/nemovideo/) in frontmatter — that could require reading local environment/install paths if implemented, though the runtime instructions do not otherwise require broad local file access.
Install Mechanism
There is no install specification and no code files (instruction-only), so nothing is written to disk by the skill itself. This minimizes install-time risk.
Credentials
Only one credential (NEMO_TOKEN) is declared as primary, which is proportionate for accessing the described API. The skill can also create an anonymous token server-side if NEMO_TOKEN is not set, reducing the need for users to provide an account token. There is a minor inconsistency: the registry metadata shown at the top listed no required config paths, but the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/). That suggests the skill may expect or prefer reading a local config file in some implementations — clarify before giving a personal account token.
Persistence & Privilege
always:false (not force-included); user-invocable and allows autonomous invocation by default — standard for skills. The skill does not request permanent system presence or attempt to modify other skills or system-wide settings in the provided instructions.
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 video-to-text-transcription-free - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-to-text-transcription-free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
Video-to-Text Transcription Free — Initial Release
- Upload MP4, MOV, AVI, or WebM (up to 500MB) for free, fast, and accurate AI speech-to-text transcription.
- Automatic setup with free token generation—no local install or paid software required.
- Simple workflow: upload your video, request transcription, and download in 1080p MP4 or subtitle format.
- Clear status updates, session management, and error handling for smooth user experience.
- Designed for students, content creators, and journalists needing quick transcripts.
元数据
常见问题
Video To Text Transcription Free 是什么？
Get text transcripts ready to post, without touching a single slider. Upload your video files (MP4, MOV, AVI, WebM, up to 500MB), say something like "transcr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 61 次。
如何安装 Video To Text Transcription Free？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-to-text-transcription-free」即可一键安装，无需额外配置。
Video To Text Transcription Free 是免费的吗？
是的，Video To Text Transcription Free 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video To Text Transcription Free 支持哪些平台？
Video To Text Transcription Free 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 Video To Text Transcription Free？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills