An AI-powered video editing skill that transforms raw podcast footage into polished, captioned, and export-ready episodes without manual effort.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install podcast-video-camera
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install podcast-video-camera using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Podcast Video Camera?
Podcast Video Camera is a sophisticated AI agent skill designed for creators who need to move from raw recording to final publication in record time. By leveraging cloud GPU rendering, it handles intensive video processing tasks like filler word removal and caption generation without requiring high-end local hardware. This tool is a centerpiece of the Openclaw Skills ecosystem for creators, allowing for seamless transitions between raw MP4, MOV, or WebM uploads and professional 1080p exports.
Built on the Nemo Video engine, the skill functions as a virtual editor. Users can simply drop their footage into the chat and provide natural language instructions. The backend interprets intent to manage multi-track timelines, including video, audio, and text overlays, ensuring that editing podcast recordings into publish-ready video episodes for podcast creators is as simple as sending a message.
Podcast Video Camera Use Cases
- Rapidly clean up a 60-minute podcast recording with two hosts on camera into a 1080p MP4.
- Automatically cut filler words, add captions, and export a clean podcast episode for social media or YouTube.
- Batch process multiple recordings within a single session to maintain consistent styling across a series.
- Perform iterative editing by refining rough cuts through natural language feedback before the final render.
- Convert various raw footage formats into high-quality, web-compatible MP4 files ready for distribution.
How Podcast Video Camera Works
- Authentication and Session Initialization: The skill checks for a NEMO_TOKEN or generates an anonymous token to start a secure editing session.
- Media Ingestion: Users upload raw video files (up to 500MB) directly to the chat, which are then transferred to the cloud render pipeline.
- Intent Processing: The AI analyzes the user's prompt (e.g., "add captions") and maps it to specific API actions using a Server-Sent Events (SSE) stream.
- Cloud Rendering: The project is queued on a cloud GPU node where video layers are composited and platform-specific compression is applied.
- State Management: The session tracks the timeline state, including video segments, background music, and text tracks for real-time updates.
- Export and Delivery: Once the render is complete, the skill provides a direct download link for the high-quality MP4 file.
Podcast Video Camera Setup
To start using this skill within the Openclaw Skills framework, ensure your environment is configured:
# Set your Nemo Video API token
export NEMO_TOKEN="your_token_here"
# The skill will automatically handle session creation via:
# POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent
No local video editing software is required as all processing occurs on remote GPU clusters.
Podcast Video Camera Data Schema & Taxonomy
The skill manages complex project data through a structured metadata taxonomy within the session state:
| Data Type | Description |
|---|---|
| Tracks (t) | Organized by type: Video (0), Audio (1), and Text (7). |
| Segments (sg) | Individual clips defined by start/end timestamps and source IDs. |
| Metadata (m) | Stores duration (d) in milliseconds and scaling/positioning info. |
| State Objects | Includes draft (current timeline), video_infos (source assets), and generated_media. |
Supported Formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.
Podcast Video Camera Advanced Features
- Auto-Captioning: High-accuracy text overlay generation synchronized with the audio track.
- Smart Trimming: Intent-based removal of "ums," "ahs," and long silences via natural language command.
- Multi-Track Compositing: Support for background music (BGM) layering with adjustable volume percentages.
- Cloud GPU Export: High-speed rendering of 1080p video at 1920x1080 or 1080x1920 (vertical) resolutions.
- Persistent Sessions: Ability to resume editing or tweak timelines without re-uploading original source files.
SKILL.md
Loading
Related Openclaw Skills
AI Tool for Videos
A cloud-powered AI video editor that automates silence trimming, captioning, and MP4 exporting through natural language commands.
Semantic Memory
A sophisticated long-term memory infrastructure for OpenClaw Agents optimized for Chinese semantic retrieval using a hybrid triple-track search engine.
AI Wedding Studio
A specialized tool for generating structured, multi-shot wedding photography packages with consistent subjects, styling, and cinematic quality.
Video Compressor for Discord
A powerful AI-driven tool that automatically compresses video files to meet Discord's 8MB file size limit without sacrificing quality.
Poetry Daily Art
An automated artistic pipeline that pairs classical Chinese poems with AI-generated landscape paintings to create elegant digital art cards.
Agentcy
Agentcy is a specialized marketing analyst skill that enables AI agents to query analytics, ad platforms, and e-commerce data for synthesized insights.
Featured*
