Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Whisper Api Stt

    1

    Transcribe audio through the OpenAI transcriptions endpoint with plain curl: pre-compress with ffmpeg, upload as multipart form data, pick whisper-1 or gpt-4o-t

    Free

    6 usesSecurity scanned
    Whisper Api Stt

    Whisper Api Stt

    Example session with this skill installed

    Transcribe interview.mp3 using the diarization model and output it with speaker labels. The recording has specific jargon about 'Kubernetes clusters'.

    • Read your context and instructions
    • Compiled the whisper api stt
    1. Compressed interview.mp3 to 4.2MB (16kHz mono).
    2. Sent to gpt-4o-transcribe-diarize.

    Output
    Speaker A: How are the Kubernetes clusters performing?
    Speaker B: We scaled the pods but the ingress controller is lagging.

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

    About this skill

    The problem

    Large audio files often exceed API limits or consume excessive bandwidth, while local transcription models lack the accuracy of specialized cloud endpoints. Managing multipart form data and parsing complex JSON segments manually is tedious and error-prone.

    What it does

    • Pre-compresses audio to mono 16 kHz Opus/MP3 using ffmpeg to fit under 25 MB limits.
    • Executes authenticated multipart uploads to OpenAI transcription endpoints using curl.
    • Parses verbose_json responses into human-readable formats with jq.
    • Implements diarization models to extract speaker labels from recordings.
    • Optimizes accuracy for technical jargon and names using prompt-injection hints.

    Frameworks & tools

    OpenAI API, ffmpeg, curl, jq, and standard Unix shell environments.

    Why this beats prompting it yourself

    This skill handles the low-level infrastructure of audio processing that standard LLM prompts ignore. It ensures files are correctly downsampled for cost-efficiency and provides the specific jq filters needed to turn raw API responses into usable transcripts immediately.

    Use cases

    • Transcribe long podcasts or meetings by compressing them for API compatibility.
    • Generate timestamped SRT or VTT files for video subtitles.
    • Identify different speakers in interview recordings using diarization models.
    • Improve transcription of technical documentation by biasing the model with specific jargon.

    Known limitations

    Requires an active OPENAI_API_KEY and local installations of ffmpeg and jq. Files that remain over 25 MB after compression must be manually chunked.

    Requires local ffmpeg and jq. Does not support automatic chunking for files that remain over 25 MB after 10x compression. Requires an OpenAI API key.

    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

    6 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

    Requires

    OpenAI

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    api.openai.com
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill automates the entire pipeline of preparing audio, handling multipart form data for OpenAI's API, and parsing the resulting JSON into clean, usable text using standard shell tools.

    You will need an active OpenAI API key, along with ffmpeg and jq installed on your local Unix-based environment (Linux, macOS, or WSL).

    The skill uses ffmpeg to downsample audio to mono 16 kHz Opus or MP3, ensuring your files stay under the 25 MB limit without sacrificing transcription quality.

    Yes, it supports the specialized diarization models to extract speaker labels and can generate timestamped SRT or VTT files for video subtitle workflows.

    You can use prompt-injection hints within the skill to bias the model toward specific technical jargon, names, or industry-specific terminology for better accuracy.

    The purchase includes the optimized shell workflows, compression configurations, and jq filtering logic needed to integrate Whisper transcription into your AI agent or automation pipeline.