Transcribe

Community

comol

transcribe

Transcribe video and audio files via Gemini API. Use when the user asks to transcribe a recording, generate a meeting summary, extract speech from video or audio, or convert speech to text. Supports mp4, mkv, webm, avi, mov, mp3, wav, ogg, m4a, flac.

Overview

Publisher	comol
Repository	`ai_rules_1c`
Skill name	`transcribe`
Stars	496
Forks	112
Bundled files	1
Links	Skill source Repository

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by comol on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/comol/ai_rules_1c/tree/main/content/skills/transcribe
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.

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/comol/ai_rules_1c.git /tmp/ai_rules_1c
mkdir -p .claude/skills
cp -r /tmp/ai_rules_1c/content/skills/transcribe .claude/skills/transcribe

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Transcribe 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 Transcribe 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 Transcribe 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.

transcribe — video and audio transcription

Transcribes audio and video files via the Gemini API (gemini-3.6-flash by default).

Modes

Generic (default)

Verbatim speech transcription with timecodes [MM:SS] and speaker identification.

Output files:

<name> - transcript.md — verbatim speech with timecodes
<name> - summary.md — short summary (with the --with-summary flag)

UI analysis (`--analyze-ui`, video only)

Detailed video analysis with breakdown of on-screen interface, navigation, and actions, plus screenshots.

Output files:

<name> - summary.md — short overview (topic, participants, decisions)
<name> - detailed.md — step-by-step chronological analysis with screen content and screenshots
<name> - transcript.md — verbatim speech with timecodes
screenshots/ — PNG frames of key moments

Usage


/transcribe <FilePath> [--output-dir DIR] [--analyze-ui] [--with-summary] [--format md|txt]

Parameter	Required	Default	Description
`FilePath`	yes	—	Path to audio / video file
`--output-dir`	no	`<file_folder>/Transcript/<name>/`	Result directory
`--analyze-ui`	no	off	UI-analysis mode (video only)
`--with-summary`	no	off	Add a summary (for generic mode)
`--format`	no	`md`	Output format: `md` or `txt`

Supported formats

Video: mp4, mkv, webm, avi, mov
Audio: mp3, wav, ogg, m4a, flac, aac, wma

Dependencies

Python packages: google-genai, python-dotenv
System: ffmpeg, ffprobe in PATH
API key: environment variable GEMINI_API_KEY, or <skill-dir>/.env with GEMINI_API_KEY=... (the script also checks supported user-skill locations and then cwd/.env). Use a named assignment GEMINI_API_KEY=<value>; a bare key without the variable name is ignored.
Model (optional): GEMINI_MODEL in the environment or the same .env files overrides gemini-3.6-flash. Existing environment variables take precedence. Empty or whitespace-only values use the default. Choose a model supporting audio/video input and text output through generate_content; see the Gemini model catalog.

Procedure

Determine FilePath and optional flags from the user's arguments.
Run the script:

powershell
$env:PYTHONUNBUFFERED = "1"
python <skill-dir>/scripts/transcribe.py "<FilePath>" [--output-dir "<OutputDir>"] [--analyze-ui] [--with-summary] [--format md|txt]

IMPORTANT: PYTHONUNBUFFERED=1 is mandatory; otherwise stdout is buffered and progress is not displayed.

On macOS / Linux use PYTHONUNBUFFERED=1 python ... instead.

The script runs long (5–15 minutes depending on length). Files > 1 hour are split automatically.
After completion, report the result paths to the user.
Read the summary (if any) or the start of the transcript and show it to the user.

Cost

Cost depends on the selected model, media token count and generated output. Check the current Gemini API pricing for GEMINI_MODEL or the default model before processing long recordings.

Limitations

Maximum ~1 hour per Gemini request (the script splits automatically)
Cyrillic file names: the script automatically copies the file to a temp location with an ASCII name
Screenshot quality depends on source video quality
Timecode accuracy +/- a few seconds
--analyze-ui with an audio file automatically falls back to generic + summary

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

scripts/transcribe.py28 KB

Frequently asked questions

What does the Transcribe AI skill do?

Why use Transcribe on TypingMind?

Because you install it once and use it with any model. Transcribe 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 Transcribe in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/comol/ai_rules_1c/tree/main/content/skills/transcribe. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Transcribe?

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 Transcribe?

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

Is the Transcribe AI skill free?

It is published on GitHub by comol. Check the repository for licensing terms. 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

Content Engine

affaan-m

CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Fal Ai Media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

Video Editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

Ai Presenter Video

Make a verified AI presenter video from script + image.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

transcribe — video and audio transcription

Modes

Generic (default)

UI analysis (--analyze-ui, video only)

Usage

Supported formats

Dependencies

Procedure

Cost

Limitations

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

UI analysis (`--analyze-ui`, video only)