An AI-driven cloud processing skill for editing video voiceovers, removing filler words, and enhancing audio quality automatically.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install vozo-ai
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 vozo-ai 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 Vozo AI?
Vozo AI is a sophisticated cloud-based tool designed specifically for content creators who need to edit and enhance voice audio within their video content. By leveraging this tool within Openclaw Skills, users can upload video files and perform complex edits—such as changing vocal tones or removing filler words—using simple natural language commands. The skill connects to a powerful cloud rendering pipeline to deliver 1080p MP4 outputs in as little as 30-60 seconds.
This skill is particularly valuable for streamlining post-production workflows. It handles everything from anonymous token management and session persistence to complex GPU-accelerated compositing. Whether you are working with talking-head recordings or social media clips, it provides a developer-friendly interface to professional-grade AI video editing capabilities.
Vozo AI Use Cases
- Automatically remove filler words from talking-head video recordings to create cleaner content.
- Change a speaker's voice tone and resonance to match specific professional standards.
- Add background music and text overlays to raw video clips using natural language prompts.
- Perform iterative video editing where the session maintains the timeline state for refinement.
How Vozo AI Works
- The skill checks for a NEMO_TOKEN in the environment or generates an anonymous token via the authentication API.
- A project session is initialized to track all media tracks and segments for the specific editing task.
- User video files (up to 500MB) are uploaded to the cloud rendering backend.
- Editing instructions are sent via a Server-Sent Events (SSE) stream, allowing for real-time processing feedback.
- The cloud GPU node composites the video layers, applies H.264 compression, and generates a draft timeline.
- The final output is rendered and a download URL is provided once the high-quality 1080p export is complete.
Vozo AI Setup
To get started with this skill, you need to configure your environment to handle the cloud backend connection. Openclaw Skills will manage the token lifecycle automatically if not provided.
# The skill looks for this environment variable
export NEMO_TOKEN="your_nemo_api_token"
# If no token is found, it performs an anonymous auth request
curl -X POST "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" \
-H "X-Client-Id: <generated_uuid>"
Ensure your configuration paths are set to ~/.config/nemovideo/ for persistent session data.
Vozo AI Data Schema & Taxonomy
The skill manages video data through a structured session state. This allows for persistent editing across multiple prompts.
| Component | Data Description |
|---|---|
draft |
A JSON object representing the timeline with tracks (t) and segments (sg). |
track_type |
Numerical IDs identifying content: 0 for Video, 1 for Audio, 7 for Text. |
video_infos |
Metadata about source files including resolution, bitrate, and duration. |
generated_media |
A registry of all rendered assets and their corresponding cloud URLs. |
session_id |
A unique string used to reference the current project state in the cloud. |
Vozo AI Advanced Features
- Real-time SSE Stream Processing: Supports long-running edit operations with active heartbeat monitoring to prevent timeouts.
- Intelligent Intent Classification: Automatically routes natural language prompts to specific actions like Export, Upload, or State queries.
- Automatic GUI Translation: Maps visual metaphors like "drag and drop" or "timeline preview" into actionable API requests.
- Multi-format Support: Handles a wide range of containers including MP4, MOV, AVI, WebM, and MKV for input and high-quality MP4 for output.
SKILL.md
Loading
Related Openclaw Skills
YouTube Editor AI
A cloud-powered AI video editing skill that automates cuts, transitions, and captioning for professional YouTube content.
Editor AI Online
A cloud-powered AI video editor that automates cutting silences, adding transitions, and exporting high-quality MP4 files.
calctl
A native macOS command-line interface built with EventKit for managing calendar events without AppleScript.
AI TikTok Editor
A cloud-powered AI video editor that transforms raw vertical footage into polished TikTok-ready clips using natural language commands.
Agency Accounts Payable Agent
An autonomous AI agent designed to manage vendor payments, maintain audit trails, and integrate financial operations into agentic workflows.
TikTok Editor AI
A cloud-powered AI video editor that transforms raw footage into polished TikTok content with simple text commands.
Featured*
