Name: Openai Whisper
Author: steipete

What breaks without openclaw whisper transcription skill

Untranscribed recordings. Manual copy from playback. Voice-to-task pipeline missing.

→

Instant audio-to-text × 220-star skill ÷ 5–15 minute setup ÷ no special infra = hours of manual work gone.

openclaw whisper transcription skill — what it actually does

Transcribe audio recordings via OpenClaw in one command.

Pass voice memos directly to agent workflows as text.

Build voice-to-task pipelines from speech to structured data.

Supports all common audio formats via the Whisper API.

Returns clean plain-text transcripts ready for downstream processing.

Security check — openclaw whisper transcription skill

Privacy score: 7/10 — accesses connected platform APIs only. Lock it: review OAuth scopes before install, confirm Linux, macOS; OpenClaw ≥1.0 compatibility.

Quick start — openclaw whisper transcription skill in 5–15 minutes

Setup time: 5–15 minutes

You need:

OpenClaw core
OpenAI API key

Install the package:

clawhub install steipete/openai-whisper

Set OPENAI_API_KEY in .env

Install the skill

Pass an audio file path to /transcribe

Receive plain-text transcript

Troubleshooting openclaw whisper transcription skill

1. Large files incur significant API cost — compress before uploading

2. whisper-1 only accepts <25MB files

Compatibility & status

Works with: Linux, macOS; OpenClaw ≥1.0 beginner Last updated: Oct 2025 ★ 220 on GitHub MIT

Official docs →

View on GitHub →

Related — more like openclaw whisper transcription skill

More by steipete

Audio files sitting unprocessed cost you insight every day. Install openclaw whisper transcription skill now.

Get it on GitHub →