video-translation

Translate and dub spoken audio in videos using subtitle files and timeline-based TTS.

526|77|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/NoizAI/skills --skill video-translation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-translation
Source: https://github.com/NoizAI/skills/tree/main/skills/video-translation
Command: npx skills add https://github.com/NoizAI/skills --skill video-translation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, python3, and includes scripts (resource) components.

What problem does it solve?

Translate and dub a video's spoken audio into another language while preserving the original video, removing the need for manual alignment, re-recording, or video editing to produce a natural, timeline-accurate dubbed output.

Core Features & Use Cases

  • Timeline-aligned dubbing: Uses subtitle timestamps to render TTS segments that match the original speech timing.
  • Subtitle translation: Reads SRT files and translates sentence-by-sentence into the target language while preserving indices and timestamps for seamless replacement.
  • Audio replacement with smart ducking: Optionally ducks original background audio where speech occurs and mixes the dubbed audio to retain ambient sounds.
  • Use Case: Localize a YouTube tutorial by downloading the video and subtitles, translating the SRT, generating timeline-accurate TTS in the target language, and producing a final video with replaced audio.

Quick Start

Translate and dub this YouTube video to English by providing the video URL and the target language and then return the path to the final_video.mp4 file.

Frequently Asked Questions about video-translation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I translate and dub a YouTube video into another language?

To translate and dub a YouTube video, this skill processes the video URL and SRT subtitles, translating the text and generating timeline-accurate TTS to produce a final video file with replaced audio.

Can I generate timeline-accurate TTS dubbing from an SRT file?

Yes, timeline-accurate TTS dubbing uses SRT subtitle timestamps to render translated speech segments that match the original video's timing, ensuring seamless audio replacement.

Does ffmpeg support mixing dubbed audio with background sound?

Yes, ffmpeg supports smart ducking during audio replacement, optionally lowering original background audio where translated speech occurs to retain ambient sounds in the final dubbed video.

What do I need to automatically translate subtitles and generate voice cloning?

You need the video URL or file, an SRT subtitle file or extraction capability, ffmpeg for media operations, Python3, and a TTS backend supporting timeline rendering and optional reference-audio cloning.

What is the best way to localize a video without manual re-recording?

The best way to localize a video without manual re-recording is using automated subtitle translation and timeline-aligned TTS dubbing, which preserves the original video while replacing spoken audio naturally.

Why does timeline-aligned dubbing require subtitle timestamps?

Timeline-aligned dubbing requires subtitle timestamps because they dictate the start and end points for rendering each TTS segment, ensuring the translated voice matches the original speech timing perfectly.