OpenMontage Localization & Dub — guide skill for dubbing & lip sync
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
Transcript-first translation of an existing video into subtitles, dubbed audio and optional lip-synced language variants
- Type: Guide · Dubbing & lip sync
- Slug:
openmontage-localization-dub - Status: live
- Publisher: Calesthio (community)
- License: AGPL-3.0
- Source: https://github.com/calesthio/OpenMontage/tree/main/skills/pipelines/localization-dub/
- Works in: Claude Code, Codex, Cursor, OpenClaw
- Requires: Python 3.10+, ffmpeg, Node.js 18+, an AI coding assistant
- Cost: Free/open source; generation billed by providers you connect
What it does
Transcript-first translation of an existing video into subtitles, dubbed audio and optional lip-synced language variants, preserving timing per locale. One of OpenMontage's 12 production pipelines: a YAML manifest (pipeline_defs/localization-dub.yaml) plus per-stage director skills in skills/pipelines/localization-dub/ that the agent reads before it calls the repo's Python tools (ffmpeg, WhisperX, scene detection, face-tracked reframe, Remotion or HyperFrames rendering). It checkpoints state, stops for approval at creative gates and self-reviews the render with ffprobe, frame samples and audio levels. Open the OpenMontage folder in your agent and ask for this kind of edit; the agent routes to the pipeline.
Use when
- Asked for a localization & dub edit of footage you already have
- Want a staged pipeline with approval gates instead of one prompt
Not for
- A single drop-in skill (it runs inside the OpenMontage repo)
Install
- Claude Code:
git clone https://github.com/calesthio/OpenMontage.git && cd OpenMontage && make setup
More dubbing & lip sync skills
- ElevenLabs Dubbing: Dub video and audio into other languages while keeping each original speaker's voice.
- ElevenLabs Dubbing (inference.sh): Dub audio or video into 29 languages while keeping the speaker's voice, via inference.sh.
- VideoLingo: One-click subtitle cutting, translation, alignment and dubbing with Netflix-style subtitle rules.
- pyVideoTrans: Full video translation: ASR, subtitle translation, multi-voice dubbing and muxing, with a headless CLI.
- OpenCreator (formerly KrillinAI): Creator workspace on Codex CLI: download, translate, dub and edit video with reusable Skills and Agents.
- Sync. lipsync MCP: Official MCP for the sync. lipsync API: re-time mouths in existing footage to new or translated audio.