Podcast Show Notes & YouTube Chapters from Audio

    1

    Local transcription (faster-whisper) or your SRT/VTT, then draft chapters and show notes, with timestamps checked against YouTube's chapter rules.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    About this skill

    Local transcription (faster-whisper) or your SRT/VTT, then draft chapters and show notes, with timestamps checked against YouTube's chapter rules. Audio and transcripts stay on your machine; only model weights download from huggingface.co on first use of a model.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Social Media.

    Tested on a short clip and a sample transcript only; real long-form episodes and the GPU path not tested. Chapter breaks are drafts to review (an extra short tail chapter can appear with --count). No speaker diarisation. Licences of individual Whisper model weights not checked.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Accounts
    Hugging Face
    Software
    Python 3faster-whisper (for transcribe)ffmpeg (for transcribe)numpy

    Permissions

    Allowed Hosts

    huggingface.co

    File Scopes

    Reads
    the
    audio
    or
    subtitle
    file
    you
    pass;
    writes
    output
    only
    with
    --out;
    model
    weights
    cached
    by
    faster-whisper

    Network: only `transcribe`, and only on first use of a model, downloads weights from huggingface.co (via faster-whisper). Audio and transcripts never leave the machine. `chapters` and `validate` are offline.

    Listed23 days ago

    What's inside

    Frequently Asked Questions

    No. Transcription runs on your machine; only the model weights download from huggingface.co the first time.

    First timestamp 00:00, at least three timestamps in ascending order, each chapter at least 10 seconds.

    No, there is no speaker diarisation.

    New in Social Media