← Back to Skills Marketplace
Video To Text Transcription
by
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
79
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install video-to-text-transcription
Description
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...
Usage Guidance
This skill will upload your video files to an external service (mega-api-prod.nemovideo.ai) and use a bearer token (NEMO_TOKEN) or obtain a 7-day anonymous token for you. Before installing: (1) confirm you are comfortable uploading the videos to that domain and review its privacy/retention policy; (2) consider supplying your own NEMO_TOKEN rather than letting the skill obtain one automatically if you want tighter control; (3) be aware the skill may access local paths when uploading files and may check common install/config paths to set an X-Skill-Platform header — this is minor but unnecessary for transcription and worth noting; (4) verify pricing/credit implications because anonymous tokens have limited free credits and some export errors reference subscription tiers. If you need higher assurance, ask the publisher for a homepage or documentation and confirm the API domain's legitimacy before use.
Capability Analysis
Type: OpenClaw Skill
Name: video-to-text-transcription
Version: 1.0.0
The skill is a functional integration for a video transcription service (nemovideo.ai). It provides clear instructions for the agent to manage authentication via an anonymous token, handle file uploads, and process video rendering through a cloud pipeline. While it requests access to its own configuration directory (~/.config/nemovideo/) and checks its installation path for platform attribution, these actions are transparently declared in the metadata and aligned with the stated purpose of the tool.
Capability Assessment
Purpose & Capability
Name and description match the actual actions: the skill uploads video files, requests a transcription/render from a remote API, and returns downloadable media. The declared primary credential (NEMO_TOKEN) is appropriate for a third‑party transcription API.
Instruction Scope
SKILL.md tells the agent to obtain/store an anonymous token, create sessions, upload local files (multipart @/path) or URLs, stream SSE messages, poll export status, and return download URLs — all expected for this service. It does reference reading or deriving headers from local install/config paths (e.g., ~/.clawhub, ~/.cursor, and ~/.config/nemovideo/), which is not strictly needed for transcription and is a minor scope creep to be aware of.
Install Mechanism
No install spec or code is provided (instruction-only), so nothing is written to disk by the skill itself. This is lowest-risk in terms of install behavior.
Credentials
Only a single service token (NEMO_TOKEN) is required and is the declared primary credential. The skill can also obtain an anonymous token itself if none is provided, which is coherent with its anonymous usage flow and reduces the need for additional secrets.
Persistence & Privilege
The skill instructs the agent to 'store' session_id and use tokens for subsequent requests (normal for sessioned APIs). It is not always-enabled and does not request elevated system-wide privileges. The documentation is vague about where/how session state is stored—this is typical but worth noting.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-to-text-transcription - After installation, invoke the skill by name or use
/video-to-text-transcription - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Video to Text Transcription skill.
- Upload video files (MP4, MOV, AVI, WebM up to 500MB) and transcribe spoken dialogue into editable text documents quickly.
- Automatically connect to backend and handle authentication, granting 100 free credits for new users.
- Cloud processing streams back 1080p MP4 or text transcript in about 1–2 minutes for typical clips.
- Supports export, balance checks, status queries, and multiple video/audio/text formats.
- Handles common errors (file size, expiration, unsupported formats) and provides user-friendly workflow guidance.
Metadata
Frequently Asked Questions
What is Video To Text Transcription?
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... It is an AI Agent Skill for Claude Code / OpenClaw, with 79 downloads so far.
How do I install Video To Text Transcription?
Run "/install video-to-text-transcription" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video To Text Transcription free?
Yes, Video To Text Transcription is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video To Text Transcription support?
Video To Text Transcription is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video To Text Transcription?
It is built and maintained by vcarolxhberger (@vcarolxhberger); the current version is v1.0.0.
More Skills