wjs-dubbing-video - Generate time-aligned TTS dubs from video and SRT
Generates a time-aligned TTS voice dub from a video and target-language SRT, replacing the original audio in an MP4 output.
Tags
Updated: 2026-10-12Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Generate time-aligned TTS audio
- Route voices by engine
- Render single-speaker dubs
- Apply visual speaker diarization
- Render multi-speaker dubs
Inputs
- Video file
- Target-language SRT file
- Voice ID
- Speaker separation request
Outputs
- Time-aligned dubbed MP4
- Dubbed audio replacing original audio
Requirements
- edge-tts installation for Edge voices
- Volcano TTS credentials for Volcano voices
- Access to the selected TTS service