Skip to content
TakoAPI
Back to skills

mh-openai-whisper-api

by mohdalhashemi98-hue

AI & LLMs
235Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Description

What This Skill Does

Transcribes audio files by sending them to OpenAI's Whisper API endpoint. Supports multiple audio formats, language hints, speaker prompts, and JSON or plain text output.

Uses OpenAI's hosted Whisper model via a single curl call, so no local model setup or GPU is needed.

When to Use It

  • Transcribing recorded meetings or interviews
  • Converting voice memos to text
  • Generating subtitles from audio clips
  • Transcribing podcast episodes
  • Extracting text from language learning recordings

Example Workflow

INPUT

User asks: transcribe my interview recording at /recordings/interview.m4a with speaker names Peter and Daniel

AGENT
  1. 1

    Receives audio file path and speaker context

  2. 2

    Calls transcribe.sh with --prompt flag set to 'Speaker names: Peter, Daniel'

  3. 3

    Sends multipart form request to /v1/audio/transcriptions with whisper-1 model

  4. 4

    Writes transcript to interview.m4a.txt in the same directory

OUTPUT

Plain text transcript saved to /recordings/interview.m4a.txt

Requirements

  • OPENAI_API_KEY environment variable

Installation

clawhub install mohdalhashemi98-hue/mh-openai-whisper-api

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links