Convert subtitle text into synced multilingual audio tracks using TTS APIs.
npx skills add https://github.com/jianshuo/claude-skills --skill wjs-dubbing-video
Please help me install this Agent Skill. Skill: wjs-dubbing-video Source: https://github.com/jianshuo/claude-skills/tree/main/wjs-dubbing-video Command: npx skills add https://github.com/jianshuo/claude-skills --skill wjs-dubbing-video
This Skill provides a quick and efficient way to add multilingual voiceovers to videos using the provided subtitles.
To dub a video with a Chinese voiceover, use the wjs-dubbing-video skill and provide the video file and subtitle file as inputs.
High-intent search queries and answers about installing and using this skill.
To add multilingual voiceovers to videos, this Skill translates subtitle text into a synced audio track using text-to-speech engines. It converts the provided subtitle files into localized speech and applies it directly to your video content.
Yes, you can use edge-tts neural networks for custom voiceovers. It allows you to choose from various voice types and adjust the speech rate and pitch to generate a localized audio track tailored to your video.
Video localization supports voiceover for multiple speakers. You can assign distinct voices using visual diarization or manual tagging to ensure each speaker in the subtitle text receives a corresponding synchronized audio track.
Yes, Python script execution is required to convert subtitles into a voiceover audio track. The Skill runs custom scripts and interacts with TTS APIs to process the text and generate the synchronized multilingual audio output.
The best way to dub a video with Chinese subtitles is to input the video and subtitle files into the Skill. It uses Volcano TTS and edge-tts to translate the text into a native-sounding Chinese voiceover synced with the video.
When using Volcano TTS for content localization, you are limited to the available voice types and languages supported by the API. Speech rate and pitch adjustments must also fall within the engine's supported parameters to ensure proper audio synthesis.
joyehuangConvert text to WAV narration at 1.2x speed via Google Gemini TTS API.
yikartCombine multiple video or image files into a single video with optional background audio.
syahraviTranscribe audio files with speaker diarization and word-level timestamps via ElevenLabs Scribe v2.
yangkun19921001Automates text-to-speech conversion using Microsoft Edge neural voices via node-edge-tts.
