Turn spoken words into written text with the OpenAI Whisper API. This skill sends audio files to OpenAI and returns a clean transcript. You can choose from different models like gpt-4o-transcribe or whisper-1.
Use the included script to transcribe meetings, podcasts, or voice notes. Add flags for speaker labels or change the output language. The script works with common audio formats like mp3, wav, and m4a.
Just set your API key and point the script to your audio file. The text appears right in your terminal or in a file. It is a fast way to get accurate transcripts without manual typing.
Global
mkdir -p ~/.claude/skills/openai-whisper-apiProject
mkdir -p .claude/skills/openai-whisper-apiSource Repository
Lark Openapi Explorerlarksuite/cli
Discover and call native Lark OpenAPIs not covered by existing CLI commands
Supabasesupabase/agent-skills
Add a database auth and APIs to your app with Supabase
Design An Interfacemattpocock/skills
Generate many different interface designs and pick the best one
Convex Quickstartget-convex/agent-skills
Rapidly set up a Convex backend for new or existing apps with one command
Convex Create Componentget-convex/agent-skills
Create reusable Convex components with isolated tables and clear APIs
Convexget-convex/agent-skills
Use this router to find the perfect Convex skill for your task
Firebase Remote Config Basicsfirebase/agent-skills
Change your app's behavior instantly without a new update
Notion Apiintellectronica/agent-skills
Automate your Notion workspace with simple API calls