← Back to Skills Marketplace
406
Downloads
1
Stars
2
Active Installs
2
Versions
Install in OpenClaw
/install video-narrator
Description
Generate SenseAudio TTS narration tracks for videos, including timestamped segments, style variants, and editor-ready voiceover exports. Use when users need...
Usage Guidance
This skill appears coherent for generating voiceover tracks, but before installing: 1) Verify the origin and trustworthiness of the SenseAudio service (https://senseaudio.cn) and obtain an API key with least privilege. 2) Confirm your environment's installer mapping for 'uv'—ensure it will install requests and pydub from official PyPI rather than fetching code from an untrusted host. 3) Keep the API key out of logs and examples as the skill recommends. 4) Because pydub relies on ffmpeg, ensure your ffmpeg binary is the expected trusted system package. 5) If you need stronger assurance, review any runtime code the skill will actually execute (there are no code files bundled here) or run it first in an isolated/test environment.
Capability Analysis
Type: OpenClaw Skill
Name: video-narrator
Version: 1.0.1
The skill is a legitimate integration for the SenseAudio TTS service (api.senseaudio.cn) designed to generate video narration. The provided Python code and instructions in SKILL.md follow standard practices for API interaction, environment variable usage, and audio processing with pydub, showing no signs of malicious intent, data exfiltration, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description (video narration, timestamped segments, editor exports) align with requested items: SENSEAUDIO_API_KEY, python3, ffmpeg, requests, and pydub — all reasonable for producing and assembling TTS audio for video.
Instruction Scope
SKILL.md instructions are scoped to preparing timed scripts, calling the SenseAudio TTS API, decoding returned audio, and optionally assembling clips locally. There are no instructions to read unrelated system files, exfiltrate extra data, or post data to endpoints outside senseaudio.cn.
Install Mechanism
Declared installs are two Python packages (requests, pydub) — typical and proportionate. The installer kind is 'uv' in metadata (unusual label in this manifest) but the packages themselves are standard PyPI libraries; no arbitrary URL downloads or archive extraction are used.
Credentials
Only a single credential is required (SENSEAUDIO_API_KEY) and it is clearly tied to the service the skill integrates with. The SKILL.md explicitly instructs to send the key only in the Authorization header and warns against logging or embedding it.
Persistence & Privilege
Skill is not always-enabled, does not request permanent system presence, and does not instruct modifications to other skills or global agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-narrator - After installation, invoke the skill by name or use
/video-narrator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Updated metadata to clarify required environment variables, binaries (python3, ffmpeg), and Python library dependencies.
- Description and workflow now emphasize timestamped segmentation, editor-friendly exports, and multiple style/voice variants.
- Strict notes on credential handling: API key must use the SENSEAUDIO_API_KEY environment variable; never place credentials in query strings or logs.
- Expanded and clarified TTS API parameters, audio formats, and model constraints according to official SenseAudio documentation.
- Improved example code for segment synthesis and local track assembly, with commentary on recommended workflows and timing strategies.
- Output and safety instructions refined for clarity and security in production use.
v1.0.0
- Major update: Migrated from "screen-narrator" (macOS live narration) to "SenseAudio Video Narrator" for professional video narration.
- Added support for API-based narration generation with timing and style matching.
- New implementation guide for preparing scripts, choosing narration style, and generating synchronized audio tracks.
- Advanced features: emphasis, pacing control, multiple narration takes, and background music integration.
- Updated API credentials and documentation to reflect the new SenseAudio platform.
Metadata
Frequently Asked Questions
What is Video Narrator?
Generate SenseAudio TTS narration tracks for videos, including timestamped segments, style variants, and editor-ready voiceover exports. Use when users need... It is an AI Agent Skill for Claude Code / OpenClaw, with 406 downloads so far.
How do I install Video Narrator?
Run "/install video-narrator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Narrator free?
Yes, Video Narrator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Narrator support?
Video Narrator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Narrator?
It is built and maintained by scikkk (@scikkk); the current version is v1.0.1.
More Skills