Video Translation
Skill OstrzeżenieTranslate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.
This skill automates the process of translating and dubbing video content by downloading the video, translating its subtitles, generating new audio using TTS, and replacing the original audio track. It requires external skills like `youtube-downloader` and `tts`, along with `ffmpeg` and a `NOIZ_API_KEY`.
Documentation
- warning:Configuration & parameter referenceWhile inputs and outputs are described, specific parameters for scripts like `download_video.py` and `tts.sh` are not fully documented with defaults or explicit precedence, relying on implicit script arguments.
License
- critical:License usabilityNo LICENSE file or SPDX identifier is present in the repository, and the README does not specify a license, making its usability uncertain.
Security
- warning:Secret ManagementThe extension requires a `NOIZ_API_KEY` and provides instructions on how to set it, but the mechanism for handling this secret (e.g., via environment variables or a config file) is not fully detailed, and there's a risk of it being exposed if not managed carefully.
- warning:Data ExfiltrationThe `NOIZ_API_KEY` is required for the TTS backend and could potentially be exfiltrated if not handled securely by the user or the `tts` skill itself. The workflow also involves passing video URLs and translated text, which could be considered sensitive depending on context.
Portability
- warning:Structural AssumptionThe script paths for dependencies like `youtube-downloader` and `tts` skills (`path/to/youtube-downloader/scripts/download_video.py`, `skills/tts/scripts/tts.sh`) assume a specific directory structure relative to the current working directory, which might break if not organized precisely as expected.
- warning:Runtime stabilityThe skill assumes the presence and specific installation paths of other skills (`youtube-downloader`, `tts`) and requires `ffmpeg` to be installed. It also requires `NOIZ_API_KEY` for the TTS backend, which could lead to failures if these prerequisites are not met.
Versioning
- warning:Release ManagementThere is no version information (e.g., `version` field in SKILL.md, `package.json`, or GitHub releases/CHANGELOG) present in the repository, and the installation instructions do not specify a version, implying reliance on the main branch.
Code Execution
- warning:ValidationWhile the workflow specifies inputs and outputs, the individual scripts (e.g., `download_video.py`, `tts.sh`, `replace_audio.sh`) do not explicitly demonstrate the use of a schema library for validating arguments beyond basic checks (like file existence) or sanitizing paths.
- warning:Error HandlingThe shell scripts use `set -euo pipefail`, which provides some error handling. However, the translation step's prompt-only instruction and the reliance on other skills' error handling means the overall workflow's error reporting might not be as structured or user-friendly as ideal, particularly for ambiguous failures.
- warning:Tool FallbackThe skill explicitly relies on other skills (`youtube-downloader`, `tts`) and tools (`ffmpeg`). While it lists them as dependencies, it does not specify if they are optional or provide a fallback path if they are not installed or available.
Compliance
- info:GDPRThe extension processes video content and potentially personal data if identifiable individuals are speaking in the video. While it doesn't explicitly submit personal data to a third party for processing beyond the TTS backend, there's no explicit sanitization mentioned for personally identifiable information within the video itself before processing.
Practical Utility
- warning:Usage examplesWhile the workflow is described with script commands, there are no concrete end-to-end examples showing sample input (video URL, target language), invocation, and the expected final video output. The examples are more procedural instructions.
- warning:Edge casesLimitations are mentioned (source video must have subtitles, long videos take time), but specific failure modes (e.g., what happens if `youtube-downloader` fails, or if TTS fails) and their recovery steps are not explicitly documented.
Safety
- warning:Halt on unexpected stateThe script uses `set -euo pipefail`, which helps halt on errors. However, there are no explicitly listed preconditions or checks for unexpected pre-state (e.g., existence of dependencies like `ffmpeg` or API keys) that would halt the workflow with a report before execution begins.
Instalacja
npx skills add noizai/skillsUruchamia Vercel skills CLI (skills.sh) przez npx — wymaga lokalnego Node.js oraz co najmniej jednego zainstalowanego agenta zgodnego ze skills (Claude Code, Cursor, Codex, …). Zakłada, że repozytorium jest zgodne z formatem agentskills.io.
Podobne rozszerzenia
YouTube Clipper Skill
90YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video
Video Processor
87Download and process videos from YouTube and other platforms. Supports video download, audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions YouTube download, video conversion, audio extraction, transcription, mp4, webm, ffmpeg, yt-dlp, or whisper transcription.
FFmpeg for Video Production
95Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
Day 5: Fetch & Digest
95AI Native Camp Day 5 콘텐츠 소화 스킬 만들기. fetch-tweet, fetch-youtube, content-digest 3개 스킬을 직접 만들고 활용한다. "5일차", "Day 5", "fetch", "콘텐츠 스킬", "트윗 스킬", "유튜브 스킬", "다이제스트 스킬" 요청에 사용.
TTS
95Use this skill whenever the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS', 'text to speech', 'speak', 'say', 'voice', 'read aloud', 'audio narration', 'voiceover', 'dubbing', or requests to turn written content into spoken audio. Also use when converting EPUB/PDF/SRT/articles to audio, cloning voices from reference audio, controlling emotion or speed in speech, aligning speech to subtitle timelines, or producing per-segment voice-mapped audio.
ElevenLabs Audio Generation
93Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.