transcribe — Local transcription & speaker diarization

    1

    Transcribe audio, video and YouTube locally on Apple Silicon, with speaker labels and optional subtitles.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Turn audio, video and YouTube media into readable transcripts on Apple Silicon. Local FluidAudio/Parakeet processing supports optional speaker diarization and produces Markdown, JSON and a run manifest, with optional SRT/VTT subtitles.

    This download contains the agent skill, setup documentation and original Apache-2.0 license. Install the separate transcribe runtime as described in README.md. Requires macOS 14+ on Apple Silicon and ffmpeg; YouTube sources also require yt-dlp.

    Media processing is local after the model cache is present. Network access is required for initial model downloads and YouTube retrieval. The skill does not silently switch to a cloud transcription service. No recordings, transcripts or credentials are included.

    Source: https://github.com/speech115/transcribe License: Apache-2.0; original license included. This listing does not replace the open-source license.

    Requires macOS 14+ on Apple Silicon, the separately installed transcribe runtime and ffmpeg. yt-dlp is needed for YouTube. Model downloads require internet initially. Transcripts and speaker labels should be reviewed for accuracy.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Reads user-selected media; writes transcripts, subtitles and local model caches. Network is used for installation, initial model downloads and optional YouTube retrieval. No cloud transcription or account connection is required.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill converts local audio/video files and YouTube links into text transcripts with speaker labels (diarization), outputting them in Markdown, JSON, and subtitle formats (SRT/VTT).

    This skill is optimized for macOS 14+ on Apple Silicon (M-series chips). You will also need 'ffmpeg' installed for media processing and 'yt-dlp' if you plan to transcribe YouTube content.

    Processing is performed locally on your machine using FluidAudio and Parakeet models. While an internet connection is needed for the initial model download and fetching YouTube videos, your media is never sent to a cloud transcription service.

    You will receive the agent skill, detailed setup documentation, and the original Apache-2.0 license; please note that you must install the separate 'transcribe' runtime as outlined in the included README.

    Unlike standard transcription tools, this skill includes speaker diarization, which identifies and labels different voices in a conversation, and it generates a run manifest for better data management.

    New in Workflow Automation

    Free