Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Local Whisper Stt

    10

    Transcribe audio fully offline with faster-whisper in Python: choose model size by accuracy budget, filter silence with VAD, and emit txt/srt/json. Use when a u

    Free

    4 usesSecurity scanned
    Local Whisper Stt

    Local Whisper Stt

    Example session with this skill installed

    Transcribe meeting_recording.mp3 using the 'small' model. I need both a text file and subtitles.

    • Read your context and instructions
    • Compiled the local whisper stt

    Processing meeting_recording.mp3...
    Language detected: English (0.98 confidence)
    VAD filter active: 12s of silence skipped.
    Transcribing with 'small' model (int8)...

    Outputs generated

    • meeting_recording.txt (Plain text)
    • meeting_recording.srt (Subtitles with timestamps)

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

    About this skill

    The problem

    Sending sensitive audio recordings to cloud APIs poses privacy risks and high costs for batch processing. Standard Whisper implementations are often too slow or resource-heavy for local development machines.

    What it does

    • Transcribes audio files fully offline using the faster-whisper CTranslate2 engine.
    • Detects languages automatically or forces specific locales for better accuracy.
    • Filters silence and background noise using Voice Activity Detection (VAD).
    • Outputs transcripts in .txt, .srt, and .json formats with precise timestamps.
    • Optimizes memory usage via int8 quantization for consumer-grade hardware.

    Frameworks & tools

    Python, faster-whisper, CTranslate2, FFmpeg, and VAD (Voice Activity Detection).

    Why this beats prompting it yourself

    This skill handles the boilerplate of setting up an efficient local inference pipeline. It includes VAD filtering to prevent hallucinated text during silence and provides pre-configured model tiers to balance speed against accuracy without trial and error.

    Use cases

    • Transcribe confidential internal meetings without cloud data leakage.
    • Generate .srt subtitle files for long-form video content locally.
    • Process massive batches of audio files without incurring per-minute API fees.
    • Create searchable text indexes from voice memos and interview recordings.

    Known limitations

    Requires FFmpeg installed on the host system. Not intended for real-time streaming transcription.

    Requires FFmpeg installed. Not designed for real-time streaming; best for file-based batch processing.

    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 3 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill allows you to transcribe audio files into text, SRT, or JSON formats locally on your own hardware, eliminating cloud costs and ensuring sensitive data never leaves your machine.

    The skill supports various model sizes (from 'tiny' to 'large-v3'), allowing you to choose the best balance between transcription accuracy and processing speed based on your available hardware.

    Your purchase includes the Python-based skill implementation, pre-configured settings for faster-whisper and VAD filtering, and a guide on how to integrate it into your existing AI agent workflows.

    You will need Python installed along with FFmpeg on your host system; the skill is optimized for consumer-grade hardware using int8 quantization to minimize memory usage.

    The skill includes integrated Voice Activity Detection (VAD) which automatically filters out silence and background noise to prevent the AI from generating 'hallucinated' text during quiet periods.

    While this skill is highly optimized for batch processing of recorded files and generating subtitles, it is not currently designed for low-latency, real-time streaming transcription.