A straightforward wrapper around OpenAI's Whisper transcription API using curl. You point it at an audio file (m4a, ogg, whatever Whisper supports), and it spits out a text transcript. Supports the usual options like language hints, custom prompts for better accuracy with speaker names, and JSON output if you need structured data. The nice touch is OPENAI_BASE_URL support, so you can swap in a local gateway or proxy without changing your workflow. It's the kind of tool you drop into a script when you need quick transcription without installing Python dependencies or dealing with the Whisper model locally. Does one thing, does it simply.
npx -y skills add steipete/clawdis --skill openai-whisper-api --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
prisma/skills
firebase/agent-skills
Dexploarer/hyper-forge
itsmostafa/aws-agent-skills
prisma/skills