cli-anything-videocaptioner
HKUDS/CLI-Anything/skills/cli-anything-videocaptioner/SKILL.md
AI-powered video captioning — transcribe speech, optimize/translate subtitles, and burn them into video via the stable VideoCaptioner backend. Free ASR and translation included.
Skill52k starsChanged 6 months ago
- Installs packages
What's in it
- cli-anything-videocaptioner
- Installation
- Usage
- Basic Commands
- REPL Mode
- Command Groups
- transcribe — Speech to subtitles
- subtitle — Optimize and translate
- synthesize — Burn subtitles into video
- process — Full pipeline
- review — Consistency check and preview
- styles — List style presets
- config — Manage settings
- download — Download online video
- JSON Output
- Backend Notes
- Target Languages
---
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.
More agent context in HKUDS/CLI-Anything
74 other files this repository gives its agents, the first 60 shown.
Skill
- cli-hub-meta-skillcli-hub-meta-skill/SKILL.md
- cli-anythingcodex-skill/SKILL.md
- cli-anything-hermeshermes-skill/SKILL.md
- cli-anythingmacrocli/SKILL.md
- cli-anythingreasonix-skill/SKILL.md
- cli-anything-adguardhomeskills/cli-anything-adguardhome/SKILL.md
- cli-anything-anygenskills/cli-anything-anygen/SKILL.md
- cli-anything-audacityskills/cli-anything-audacity/SKILL.md
- cli-anything-blenderskills/cli-anything-blender/SKILL.md
- cli-anything-browserskills/cli-anything-browser/SKILL.md
- cli-anything-calibreskills/cli-anything-calibre/SKILL.md
- cli-anything-ccswitchskills/cli-anything-ccswitch/SKILL.md
- cli-anything-chromadbskills/cli-anything-chromadb/SKILL.md
- cli-anything-cloudanalyzerskills/cli-anything-cloudanalyzer/SKILL.md
- cli-anything-cloudcompareskills/cli-anything-cloudcompare/SKILL.md
- cli-anything-comfyuiskills/cli-anything-comfyui/SKILL.md
- cli-anything-dify-workflowskills/cli-anything-dify-workflow/SKILL.md
- cli-anything-drawioskills/cli-anything-drawio/SKILL.md
- cli-anything-eez-studioskills/cli-anything-eez-studio/SKILL.md
- cli-anything-eth2-quickstartskills/cli-anything-eth2-quickstart/SKILL.md
- cli-anything-exaskills/cli-anything-exa/SKILL.md
- cli-anything-firefly-iiiskills/cli-anything-firefly-iii/SKILL.md
- cli-anything-freecadskills/cli-anything-freecad/SKILL.md
- cli-anything-gimpskills/cli-anything-gimp/SKILL.md
- cli-anything-godotskills/cli-anything-godot/SKILL.md
- cli-anything-inkscapeskills/cli-anything-inkscape/SKILL.md
- cli-anything-intelwatchskills/cli-anything-intelwatch/SKILL.md
- cli-anything-iterm2-ctlskills/cli-anything-iterm2-ctl/SKILL.md
- cli-anything-iterm2skills/cli-anything-iterm2/SKILL.md
- cli-anything-joplinskills/cli-anything-joplin/SKILL.md
- cli-anything-jumpserverskills/cli-anything-jumpserver/SKILL.md
- cli-anything-kdenliveskills/cli-anything-kdenlive/SKILL.md
- cli-anything-kritaskills/cli-anything-krita/SKILL.md
- cli-anything-libreofficeskills/cli-anything-libreoffice/SKILL.md
- cli-anything-live2dskills/cli-anything-live2d/SKILL.md
- cli-anything-lldbskills/cli-anything-lldb/SKILL.md
- cli-anything-macrocliskills/cli-anything-macrocli/SKILL.md
- cli-anything-mailchimpskills/cli-anything-mailchimp/SKILL.md
- cli-anything-mermaidskills/cli-anything-mermaid/SKILL.md
- cli-anything-minimaxskills/cli-anything-minimax/SKILL.md
- cli-anything-mubuskills/cli-anything-mubu/SKILL.md
- cli-anything-musescoreskills/cli-anything-musescore/SKILL.md
- cli-anything-n8nskills/cli-anything-n8n/SKILL.md
- cli-anything-notebooklmskills/cli-anything-notebooklm/SKILL.md
- cli-anything-novitaskills/cli-anything-novita/SKILL.md
- cli-anything-nsight-graphicsskills/cli-anything-nsight-graphics/SKILL.md
- cli-anything-nsloggerskills/cli-anything-nslogger/SKILL.md
- cli-anything-obsidianskills/cli-anything-obsidian/SKILL.md
- cli-anything-obs-studioskills/cli-anything-obs-studio/SKILL.md
- cli-anything-ollamaskills/cli-anything-ollama/SKILL.md
- cli-anything-openrefineskills/cli-anything-openrefine/SKILL.md
- cli-anything-openscreenskills/cli-anything-openscreen/SKILL.md
- cli-anything-pm2skills/cli-anything-pm2/SKILL.md
- cli-anything-qgisskills/cli-anything-qgis/SKILL.md
- cli-anything-quietshrinkskills/cli-anything-quietshrink/SKILL.md
- cli-anything-rekordboxskills/cli-anything-rekordbox/SKILL.md
- cli-anything-renderdocskills/cli-anything-renderdoc/SKILL.md
- cli-anything-rmsskills/cli-anything-rms/SKILL.md
- cli-anything-safariskills/cli-anything-safari/SKILL.md
- cli-anything-sboxskills/cli-anything-sbox/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

