Videocaptioner logo

Videocaptioner

CommunityPopular
WEIFENG2333
videocaptioner

Process video subtitles — transcribe speech, optimize/translate text, burn styled subtitles into video. Use when you need to add subtitles to a video, transcribe audio, translate subtitles, or customize subtitle styles.

Overview

PublisherWEIFENG2333
RepositoryVideoCaptioner
Skill namevideocaptioner
Stars
16K
Forks
1.4K
Bundled files
Instructions only
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WEIFENG2333 on GitHub. Read the source before you install it.

Installation

Install the Videocaptioner AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/WEIFENG2333/VideoCaptioner.git /tmp/VideoCaptioner
mkdir -p .claude/skills
cp -r /tmp/VideoCaptioner/skills .claude/skills/videocaptioner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Videocaptioner in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Videocaptioner on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Videocaptioner is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

VideoCaptioner CLI

AI-powered video captioning: transcribe speech → optimize subtitles → translate → burn into video with beautiful styles.

When to use

  • User wants to add subtitles to a video
  • User wants to transcribe audio/video to text
  • User wants to translate subtitles to another language
  • User wants to customize subtitle appearance (colors, fonts, rounded backgrounds)
  • User wants to download and subtitle online videos

Before you start

Always run videocaptioner <command> --help first to check the latest options and defaults before executing a command. The examples below are common patterns, but --help is the source of truth.

  • Install: pip install videocaptioner
  • FFmpeg required for video synthesis (brew install ffmpeg on macOS)
  • Free (no API key): transcription (bijian/jianying), translation (Bing/Google)
  • Requires LLM API key: subtitle optimization, subtitle re-segmentation, LLM translation. Set via OPENAI_API_KEY env var or --api-key flag

Common scenarios

1. Give a Chinese video English subtitles (one command, all free)

bash
videocaptioner process video.mp4 --asr bijian --translator bing --target-language en \
  --subtitle-mode hard --quality high -o output.mp4

2. Transcribe a video to SRT (free)

bash
videocaptioner transcribe video.mp4 --asr bijian -o output.srt

# Output as JSON format to a directory
videocaptioner transcribe video.mp4 --asr bijian --format json -o ./subtitles/

3. Translate existing subtitles

bash
# Free Bing → English, bilingual output with translation above original
videocaptioner subtitle input.srt --translator bing --target-language en --layout target-above -o translated.srt

# Free Google → Japanese, translation only (discard original text)
videocaptioner subtitle input.srt --translator google --target-language ja --no-optimize --layout target-only -o output_ja.srt

# High quality LLM translation with reflective mode
videocaptioner subtitle input.srt --translator llm --target-language en --reflect \
  --api-key $OPENAI_API_KEY -o output_en.srt

4. Full pipeline with beautiful styled subtitles

bash
# Anime-style subtitles (warm color + orange outline), high quality video
videocaptioner process video.mp4 --asr bijian --translator bing --target-language ja \
  --subtitle-mode hard --style anime --quality high -o output_ja.mp4

# Modern rounded background subtitles
videocaptioner process video.mp4 --asr bijian --translator google --target-language ko \
  --subtitle-mode hard --render-mode rounded -o output_ko.mp4

# Custom colors: white text with red outline, ultra quality
videocaptioner process video.mp4 --asr bijian --translator bing --target-language en \
  --subtitle-mode hard --quality ultra \
  --style-override '{"outline_color": "#ff0000", "primary_color": "#ffffff"}' -o output_en.mp4

5. Subtitle only, output as ASS format (no video synthesis)

bash
videocaptioner process video.mp4 --asr bijian --translator bing --target-language en \
  --format ass --no-synthesize -o ./output/

6. Step-by-step control (transcribe → translate → synthesize separately)

bash
# Step 1: Transcribe
videocaptioner transcribe video.mp4 --asr bijian -o video.srt

# Step 2: Translate (bilingual, original text above translation)
videocaptioner subtitle video.srt --translator bing --target-language en --layout source-above -o video_en.srt

# Step 3: Burn into video with rounded background, high quality
videocaptioner synthesize video.mp4 -s video_en.srt --subtitle-mode hard \
  --render-mode rounded --quality high -o video_with_subs.mp4

7. Process audio file (auto-skips video synthesis)

bash
videocaptioner process podcast.mp3 --asr bijian --translator bing --target-language en -o ./output/

8. Transcribe other languages (whisper-api)

bash
videocaptioner transcribe french_video.mp4 --asr whisper-api \
  --whisper-api-key $OPENAI_API_KEY --language fr -o french.srt

9. Only optimize subtitles with LLM (fix ASR errors, no translation)

bash
videocaptioner subtitle raw_subtitle.srt --no-translate --api-key $OPENAI_API_KEY -o optimized.srt

10. Custom rounded background style with custom font

bash
videocaptioner synthesize video.mp4 -s subtitle.srt --subtitle-mode hard \
  --style-override '{"text_color": "#ffffff", "bg_color": "#000000cc", "corner_radius": 10, "font_size": 36}' \
  --font-file ./NotoSansSC.ttf --quality high -o styled_video.mp4

Command reference

CommandPurpose
transcribeSpeech → subtitles. Engines: bijian(free) jianying(free) whisper-api whisper-cpp
subtitleOptimize (LLM) and/or translate (LLM/Bing/Google) subtitle files
synthesizeBurn subtitles into video with customizable styles
processFull pipeline: transcribe → optimize → translate → synthesize
downloadDownload video from YouTube, Bilibili, etc.
configManage settings (show set get path init)
styleList all subtitle style presets with parameters

Run videocaptioner <command> --help for full options.

Subtitle styles

Two rendering modes for beautiful subtitles:

ASS mode (default) — outline/shadow style:

  • Presets: default (white+black outline), anime (warm+orange outline), vertical (portrait videos)
  • Customizable fields: font_name, font_size, primary_color, outline_color, outline_width, bold, spacing, margin_bottom

Rounded mode — modern rounded background boxes:

  • Preset: rounded (dark text on semi-transparent background)
  • Customizable fields: font_name, font_size, text_color, bg_color (#rrggbbaa), corner_radius, padding_h, padding_v, margin_bottom

Style options only work with --subtitle-mode hard.

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.

Environment variables

VariablePurpose
OPENAI_API_KEYLLM API key
OPENAI_BASE_URLLLM API base URL

Exit codes

0 success · 2 bad arguments · 3 file not found · 4 missing dependency · 5 runtime error

Tips

  • Use -q for scripting (stdout = result path only)
  • Bing/Google translation is free, no API key needed
  • bijian/jianying ASR is free but only supports Chinese & English
  • Run videocaptioner style to see all style presets

Frequently asked questions

What does the Videocaptioner AI skill do?

Process video subtitles — transcribe speech, optimize/translate text, burn styled subtitles into video. Use when you need to add subtitles to a video, transcribe audio, translate subtitles, or customize subtitle styles.

Why use Videocaptioner on TypingMind?

Because you install it once and use it with any model. Videocaptioner is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Videocaptioner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WEIFENG2333/VideoCaptioner/tree/master/skills. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Videocaptioner?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Videocaptioner?

As many as you like. As long as a model supports skills, you can use Videocaptioner with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Videocaptioner AI skill free?

Yes. It is published on GitHub by WEIFENG2333 under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇