Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

cli-anything-videocaptioner — Claude Code skill: setup and features

Transcribes speech, translates subtitles into 38 languages, and burns captions into video using the VideoCaptioner backend. Useful when preparing video assets directly from the terminal.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add HKUDS/CLI-Anything --skill cli-anything-videocaptioner -a claude-code
Open on GitHub

What cli-anything-videocaptioner does

This skill gives your agent CLI access to cli-anything-videocaptioner for video subtitling. It handles speech recognition via the default free bijian engine or Whisper, splits and translates lines into 38 languages with Bing or Google, and hard-burns or soft-burns captions into the media container. Agents can pass --json to receive structured machine-readable responses.

The review command checks drift against an approved transcript via --review-script and can render a single preview frame instead of encoding the entire video. That saves processing time if speech recognition mistranscribes technical terms.

The upstream videocaptioner 1.4.1 backend strictly requires Python 3.10 to 3.12, so higher versions will fail. You also need FFmpeg installed on your machine for video synthesis. Subtitle styling depends on backend capabilities, which can be checked beforehand with styles.

What it helps with

  • transcribe speech from video files into SRT, ASS, or TXT formats
  • translate subtitles into 38 target languages via Bing or Google
  • verify subtitle consistency against an approved text script
  • render a one-frame preview to check subtitle appearance before exporting
  • burn soft or hard subtitles into videos using FFmpeg

Example prompts for the agent

  • Transcribe video.mp4 using the bijian ASR engine and output to SRT format
  • Translate input.srt to German using the Bing translator and keep only the target language
  • Check subtitles.srt against approved_script.txt and generate a preview frame from video.mp4 at 5 seconds

How to install cli-anything-videocaptioner

1Skills CLI (Vercel)

npx skills add HKUDS/CLI-Anything --skill cli-anything-videocaptioner -a claude-code

2Manually: put the files in place

~/.claude/skills/cli-anything-videocaptioner/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cli-anything-videocaptioner/

From the same set18

The whole set →
cli-hub-meta-skill HKUDS A skill that gives agents a catalog of professional command-line tools built for AI. Search, install, and run CLIs for video, design, AI, and development without leaving your editor. Claude Code CX Codex Cursor +1 5,300installs cli-anything HKUDS Builds a Python harness with Click commands for any GUI application or repository. Generates REPL, tests, and docs following the CLI-Anything methodology. Claude Code CX Codex Cursor +1 2,100installs cli-anything-blender HKUDS A skill that adds a stateful command-line interface for editing Blender 3D scenes. Use it when an agent needs to assemble a scene, assign materials, or render a frame without manual clicking. Claude Code CX Codex Cursor +1 941installs cli-anything-obsidian HKUDS Manage an Obsidian vault from the terminal: read, create, search, and update notes or run editor commands. It suits agents that need to work without the GUI. Claude Code CX Codex Cursor +1 917installs cli-anything-notebooklm HKUDS Experimental harness to manage Google NotebookLM through a local CLI. It lets agents list notebooks, query sources, generate artifacts, and download files. Claude Code CX Codex Cursor +1 801installs cli-anything-libreoffice HKUDS Skill for creating and editing Writer, Calc, and Impress documents from the CLI without a GUI. Produces real ODF files (ZIP with XML) — useful when an AI agent needs to assemble a report, spreadsheet, or presentation programmatically. Claude Code CX Codex Cursor +1 669installs cli-anything-drawio HKUDS A command-line harness over Draw.io: the skill hands your agent commands to build a diagram step by step and export it to PNG, PDF or SVG. Claude Code CX Codex Cursor +1 666installs cli-anything-freecad HKUDS Turns FreeCAD into a scriptable CLI for your agent: 258 commands for primitives, sketches, PartDesign features and headless export. Claude Code CX Codex Cursor +1 643installs

Similar

debug-inference NVIDIA Debugs failed inference in OpenShell as provider-authorized traffic: native endpoint, provider profile, sandbox attachment, host-local model servers. Claude Code CX Codex Cursor +1 433installs firecrawl-knowledge-base firecrawl This skill crawls web pages with Firecrawl and structures them into local Markdown files. It helps prepare clean RAG chunks or fine-tuning datasets. Claude Code CX Codex Cursor +1 32,500installs ecosystem-primer langchain-ai Guides framework selection across LangChain, LangGraph, and Deep Agents before writing code. Maps requirements to the right layer, env vars, and quickstarts. Claude Code CX Codex Cursor +1 8,000installs seedance-20 Emily2040 A skill that steers the agent through Seedance 2.0 video work: brief, surface checks, then a compact prompt for the mode you asked for. Claude Code CX Codex Cursor +1 481installs api-gateway-mcp-server official google Configures Google Cloud API Gateway as a remote MCP server over HTTP. It exposes REST APIs as tools for AI agents using annotated OpenAPI 3.x specs. Claude Code Gemini CLI CX Codex 499installs threejs-audio-generator majidmanzarpour A skill that turns ElevenLabs into game audio for Three.js: effects, loops, music and voice lines, written straight into the project. Claude Code CX Codex Cursor +1 2,900installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about cli-anything-videocaptioner

How do I install cli-anything-videocaptioner in Claude Code?

Run npx skills add HKUDS/CLI-Anything --skill cli-anything-videocaptioner -a claude-code. You also need Python packages via pip install cli-anything-videocaptioner and pip install videocaptioner.

What does cli-anything-videocaptioner do?

It automates speech transcription, subtitle translation across 38 languages, script drift checks, and video subtitle burning.

What prerequisites are required?

The backend requires Python 3.10-3.12 (with Python 3.12 preferred) and FFmpeg installed on your system for video rendering.

Source text

SKILL.md · Apache-2.0
---
name: "cli-anything-videocaptioner"
description: >-
  AI-powered video captioning — transcribe speech, optimize/translate subtitles, and burn them into video via the stable VideoCaptioner backend. Free ASR and translation included.
---

# cli-anything-videocaptioner

AI-powered video captioning tool. Transcribe speech → optimize subtitles → translate → burn into video.

## Installation

```bash
pip install cli-anything-videocaptioner
```

**Prerequisites:**
- Python 3.10-3.12 (`videocaptioner` 1.4.1 requires `>=3.10,<3.13`)
- `videocaptioner` must be installed (`pip install videocaptioner`)
- FFmpeg required for video synthesis

## Usage

### Basic Commands

```bash
# Show help
cli-anything-videocaptioner --help

# Start interactive REPL mode
cli-anything-videocaptioner

# Transcribe a video (free, no setup)
cli-anything-videocaptioner transcribe video.mp4 --asr bijian

# Translate subtitles (free Bing translator)
cli-anything-videocaptioner subtitle input.srt --translator bing --target-language en

# Full pipeline: transcribe → translate → burn subtitles
cli-anything-videocaptioner process video.mp4 --asr bijian --translator bing --target-language en --subtitle-mode hard

# Review subtitle/script consistency before a final hard-burn
cli-anything-videocaptioner synthesize video.mp4 -s subtitles.srt \
  --subtitle-mode hard \
  --review-script approved_script.txt

# Render a one-frame subtitle preview for review
cli-anything-videocaptioner review subtitles.srt \
  --script approved_script.txt \
  --preview-video video.mp4 \
  --preview-output review_5s.png

# JSON output (for agent consumption)
cli-anything-videocaptioner --json transcribe video.mp4 --asr bijian
```

### REPL Mode

When invoked without a subcommand, the CLI enters an interactive REPL session:

```bash
cli-anything-videocaptioner
# Enter commands interactively with tab-completion and history
```

## Command Groups

### transcribe — Speech to subtitles
```
transcribe <input> [--asr bijian|jianying|whisper-api|whisper-cpp] [--language CODE] [--format srt|ass|txt|json] [-o PATH]
```
- `bijian` (default): Free, Chinese & English, no setup
- `whisper-api`: All languages, requires `--whisper-api-key`

### subtitle — Optimize and translate
```
subtitle <input.srt> [--translator llm|bing|google] [--target-language CODE] [--layout target-above|source-above|target-only|source-only] [--no-optimize] [--no-translate] [-o PATH]
```
- Three steps: Split → Optimize → Translate
- Bing/Google translators are free
- 38 target languages supported (BCP 47 codes)

### synthesize — Burn subtitles into video
```
synthesize <video> -s <subtitle> [--subtitle-mode soft|hard] [--quality ultra|high|medium|low] [-o PATH] [--review-script PATH] [--max-script-diff-ratio FLOAT]
```
- Mirrors the stable backend synthesize surface
- Subtitle look is controlled by the subtitle asset/backend version, not extra harness flags
- `--review-script` checks subtitle/script drift before the final export
- Lower `--max-script-diff-ratio` when copy accuracy matters more than resilience

### process — Full pipeline
```
process <input> [--asr ...] [--translator ...] [--target-language ...] [--subtitle-mode ...] [--layout ...] [--no-optimize] [--no-translate] [--no-synthesize] [-o PATH]
```

### review — Consistency check and preview
```
review <input.srt|input.ass> [--script PATH] [--max-diff-ratio FLOAT] [--preview-video PATH] [--preview-at TC] [--preview-output PATH]
```
- Detects subtitle/script drift before a hard-burn
- Can render a single review frame instead of producing a full final video

### styles — List style presets
```
styles
```
- Reports whether the installed backend exposes preset styling support

### config — Manage settings
```
config show
config set <key> <value>
```

### download — Download online video
```
download <URL> [-o DIR]
```

## JSON Output

All commands support `--json` for machine-readable output:
```bash
cli-anything-videocaptioner --json transcribe video.mp4 --asr bijian
# {"output_path": "/path/to/output.srt"}
```

## Backend Notes

- The upstream backend currently requires Python `>=3.10,<3.13`; prefer Python `3.12` for matrix runs.
- Advanced synthesize-time style flags are backend-version dependent. Use `styles` to check whether the installed backend exposes them.
- Compatibility flags such as `layout`, `render_mode`, `style`, `style_override`, and `font_file` should be treated as non-stable unless `styles` and the installed backend confirm they are supported.

## Target Languages

BCP 47 codes: `zh-Hans` `zh-Hant` `en` `ja` `ko` `fr` `de` `es` `ru` `pt` `it` `ar` `th` `vi` `id` and 23 more.

© HKUDS · Apache-2.0 · HKUDS/CLI-Anything

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor