omnicaptions-transcribe

omnicaptions-transcribe is a skill for Claude Code from lattifai/omni-captions-skills. It costs 38 tokens per session (1,368 once invoked), scanned A, original, MIT.

A tool workflow for turning audio or video into structured text with timestamps, speaker labels, and chapters. It accepts YouTube links and local media files, and uses existing captions when available.

In plain words
What is it for?
Use it for interviews, podcasts, lectures, and other recordings when you need a timestamped transcript or chapter outline.
Why use it?
It avoids manually transcribing recordings and can preserve useful structure such as who spoke and when.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the omnicaptions plugin — 5 skills shipped together

Good fit Use it for interviews, podcasts, lectures, and other recordings when you need a timestamped transcript or chapter outline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lattifai/omni-captions-skills/omnicaptions-transcribe
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lattifai/omni-captions-skills --skill omnicaptions-transcribe
Clone the repo
git clone --depth 1 https://github.com/lattifai/omni-captions-skills

Made for: Claude Code.

Or install omnicaptions, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for omnicaptions-transcribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-transcribe/github.svg)](https://agentmods.dev/skills/lattifai/omni-captions-skills/omnicaptions-transcribe)
Your own site
<a href="https://agentmods.dev/skills/lattifai/omni-captions-skills/omnicaptions-transcribe"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-transcribe/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omnicaptions-transcribe

Your own site · 80×15
<a href="https://agentmods.dev/skills/lattifai/omni-captions-skills/omnicaptions-transcribe"><img src="https://agentmods.dev/badge/skills/lattifai/omni-captions-skills/omnicaptions-transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01368
Opus 5 $0.00019 $0.00684
Sonnet 5 $0.00008 $0.00274
Haiku 4.5 $0.00004 $0.00137

Measured 12d ago against content hash 33f37f1b3f9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

omnicaptions-transcribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/omnicaptions-transcribe/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Transcription

Transcribe audio/video using Google Gemini API with structured markdown output.

YouTube Video Workflow

Important: Check for existing captions before transcribing:

1. Check captions: yt-dlp --list-subs "URL"
2. Has caption → Use /omnicaptions:download to get existing captions (better quality)
3. No caption → Transcribe directly with URL (don't download first!)

Confirm with user: Before transcribing, ask if they want to check for existing captions first.

URL & Local File Support

Gemini natively supports YouTube URLs - no need to download, just pass the URL directly:

# YouTube URL (recommended, no download needed)
omnicaptions transcribe "https://www.youtube.com/watch?v=VIDEO_ID"

# Local files
omnicaptions transcribe video.mp4

Note: Output defaults to current directory unless user specifies -o.

When to Use

  • Video URLs - YouTube, direct video links (Gemini native support)
  • Transcribing podcasts, interviews, lectures
  • Need verbatim transcript with timestamps and speaker labels
  • Want auto-generated chapters from content
  • Mixed-language audio (code-switching preserved)

When NOT to Use

  • Video has existing captions - Use /omnicaptions:download to get existing captions first
  • Need real-time streaming transcription (use Whisper)
  • Audio >2 hours (Gemini upload limit)
  • Want translation instead of transcription

Quick Reference

Method Description
transcribe(path) Transcribe file or URL (sync)
translate(in, out, lang) Translate captions
write(text, path) Save text to file

Setup

pip install omni-captions-skills --extra-index-url https://lattifai.github.io/pypi/simple/

API Key

Priority: GEMINI_API_KEY env → .env file → ~/.config/omnicaptions/config.json

If not set, ask user: Please enter your Gemini API key (get from https://aistudio.google.com/apikey):

Then run with -k <key>. Key will be saved to config file automatically.

Read the full file on GitHub · 166 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 166 lines · 38 tokens per session scan A 33f37f1b3f9d

Subscribe to this mod's changes

omnicaptions-transcribe is a skill published in the GitHub repository lattifai/omni-captions-skills (22 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,368 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens