Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    WhatsApp Voice Note Transcribe

    1

    Transcribe and translate voice notes 100% on your own machine with faster-whisper. Built for Arabic, including Egyptian dialect.

    Free

    4 usesSecurity scanned
    WhatsApp Voice Note Transcribe

    WhatsApp Voice Note Transcribe

    Example session with this skill installed

    Transcribe this WhatsApp voice note 'feedback.ogg'. It's in Arabic. Check if the customer mentions any issues with the new subscription flow or app names.

    • Read your context and instructions
    • Compiled the whatsapp voice note

    I transcribed feedback.ogg (21 seconds) on this machine with faster-whisper large-v3 on your GPU: 4 s to load, 3 s to transcribe. No audio or text left your computer.

    Short answer

    Subscription issue: yes. The customer says the subscription won't renew from their iPhone, and reopening the app didn't help.
    App names: none clearly said. One word at 00:15–00:17 is missing from the transcript and may be an app name. Please listen to that part.
    Not said: whether an error message appeared, or when the problem started.

    Transcript and translation

    TimeArabic (as transcribed)English
    00:00–00:04السلام عليكم، كنت بحاول ادخل على البروفايل بتاعيHi, I was trying to get into my profile
    00:04–00:11بس الصبسكريبشن مش راضي يتجدد خالص من الايفونBut the subscription [?] won't renew at all from the iPhone
    00:11–00:17جربت افتح الابلكيشن كذا مرة ومفيش فايدة، حتى نزلتI tried opening the app several times, no use. I even downloaded [?] (a word is missing here)
    00:17–00:21بس برضو نفس المشكلةbut it's still the same problem.

    Key quote: «الصبسكريبشن مش راضي يتجدد خالص من الايفون», "the subscription won't renew at all from the iPhone".

    Reliability

    TimeTranscribedLikely meaning
    00:04الصبسكريبشن"subscription", an English word written phonetically
    00:15–00:17حتى نزلت …A word is missing after "I even downloaded", possibly an app name. Worth listening to.

    Files

    • feedback/transcript_ar.txt: the raw transcript, unchanged
    • feedback/transcript_en.txt: the translation, with [?] marks
    • feedback/confidence_log.txt: per-segment confidence

    Next steps

    1. Listen to 00:15–00:17 to catch the missing word.
    2. If it's a bug report, ask the customer for their iOS version and any error message. They didn't mention either.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop sending sensitive audio to cloud APIs. This skill transcribes WhatsApp voice notes and other audio entirely on your own machine with faster-whisper (Whisper large-v3). The audio and transcripts never leave your computer.

    It's built for Arabic voice notes, including Egyptian and other dialects with English words mixed in, and works with any language Whisper supports.

    What it does

    • Local transcription: turns .ogg/.opus, .m4a, .mp3, .wav and anything else ffmpeg can read into a timestamped transcript, with no cloud calls.
    • Honest translation: Claude writes an English translation and marks every uncertain word with [?] instead of guessing.
    • Answers your questions: give it questions (for example, survey questions) and it quotes the key sentences in the original language with a translation, and says plainly when something wasn't answered.
    • Reliability report: lists the least reliable segments and what they probably say. Whisper often drops brand names and English words in dialect speech, so you know what to listen to again.
    • GPU or CPU: uses an NVIDIA GPU if you have one (about 17 s for a 2.5-minute note) and falls back to the CPU (about real time).

    Privacy

    • Offline by default. The model downloads once, and only after you approve it.
    • The original audio is never modified. Outputs go in a new folder next to it.

    Requirements

    • Python 3.10+ and ffmpeg
    • About 3 GB of disk for the Whisper large-v3 model (a one-time download)
    • An agent that can run shell commands on your machine. Tested with Claude Code.

    Source and updates

    Open source (MIT): https://github.com/hesham-abboud/whatsapp-voice-note-transcribe

    • Dialect transcripts need a human check: Whisper often drops or garbles brand and app names and English words mixed into Arabic. The skill flags these segments, but can't recover words the model never wrote.
    • Requires ffmpeg, Python 3.10+ and an agent with shell access. Tested only with Claude Code on Windows 11.
    • One-time model download: about 3 GB for large-v3 (or 1.5 GB for medium). Network proxies may block it, in which case the skill stops and reports the blocked host.
    • CPU transcription runs at about real time (a 2.5-minute note takes about 2 minutes). An NVIDIA GPU with CUDA 12 is about 6x faster.
    • GPU and CPU output can differ slightly, and GPU runs occasionally add a short made-up phrase on the last second of audio. Check the final line.

    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

    4 uses

    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

    Requires

    Hugging Face
    GitHub
    Python 3.10+
    FFmpeg
    Git
    About 3 GB free disk space
    Python
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    huggingface.co
    github.com

    File Scopes

    **/*.ogg
    **/*.opus
    **/*.m4a
    **/*.mp3
    **/*.wav
    ~/.whatsapp-voice-note-transcribe/**
    ~/.cache/huggingface/**

    Audio files are only read, never modified. Outputs (transcript_<lang>.txt, transcript_en.txt, confidence_log.txt) are written to a new folder next to the audio file, named after it. The CLI is installed into ~/.whatsapp-voice-note-transcribe, and the Whisper model is cached in ~/.cache/huggingface. Network use: github.com (installing the CLI, only if the bundled source isn't available) and huggingface.co (one-time model download of about 3 GB). Both need the user's approval first. Transcription itself is fully offline. No audio or transcripts are ever uploaded.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The audio is transcribed entirely on your machine with faster-whisper and is never uploaded anywhere. The transcript text is then read by your AI agent to write the translation and summary, so it is processed by your agent’s model provider (for example, Anthropic for Claude Code) under their terms, like any other text in your chat. If the transcript itself is too sensitive for that, use only the CLI and read the transcript files yourself.

    Yes. Whisper large-v3 handles Arabic with English words mixed in, but it often drops or garbles English terms and brand names in dialect speech. The skill doesn’t fix those words. It flags the unreliable segments, marks uncertain words with [?], and suggests what they probably say, so you know which parts to listen to again.

    Python 3.10+, ffmpeg, git, and an agent that can run shell commands on your machine (tested with Claude Code). Disk: about 3.5 GB (3.1 GB model plus Python packages), or about 4.5 GB with NVIDIA GPU support.

    No. The skill includes the instructions and the CLI source code. The Whisper model (about 3.1 GB for large-v3, 1.5 GB for medium) is downloaded once on first use, only after you approve it, and then cached locally. After that, transcription runs fully offline.

    No. On a modern laptop CPU it runs at about real time (a 2.5-minute note takes about 2 minutes). An NVIDIA GPU with CUDA 12 is about 6x faster (about 17 seconds). The skill uses the GPU automatically when available and falls back to the CPU.

    Yes. You get the original transcript with timestamps (transcript_ar.txt) and a line-by-line English translation with [?] marks (transcript_en.txt), saved next to your audio file. In the chat you also get answers to your questions and a table of the least reliable segments.

    Any SKILL.md agent that can run shell commands on your machine should work, but it has only been tested with Claude Code on Windows 11.

    Yes, for any language Whisper supports. Ask for the language (for example “it’s in English”), or let it detect the language automatically.

    New in LLM Ops