← Back to Skills Marketplace
Openai Whisper
by
Peter Steinberger
· GitHub ↗
· v1.0.0
85107
Downloads
325
Stars
2127
Active Installs
1
Versions
Install in OpenClaw
/install openai-whisper
Description
Local speech-to-text with the Whisper CLI (no API key).
Usage Guidance
Install this only if you trust your Homebrew setup and the `openai-whisper` package. Expect model files to be downloaded and cached locally, and treat generated transcripts as potentially sensitive because they reflect the audio files you choose to process.
Capability Analysis
Type: OpenClaw Skill
Name: openai-whisper
Version: 1.0.0
The skill bundle is benign. It provides instructions for using the `openai-whisper` CLI for local speech-to-text transcription. The `SKILL.md` defines the skill, its purpose, and installation via `brew install openai-whisper`, which is a standard and legitimate method. Example commands demonstrate local file processing, and the mention of models downloading to `~/.cache/whisper` is expected behavior for the `whisper` CLI. There is no evidence of malicious intent, data exfiltration, unauthorized execution, prompt injection against the agent, or obfuscation.
Capability Assessment
Purpose & Capability
The stated purpose, required binary, and examples all align with local speech-to-text or translation using the `whisper` CLI.
Instruction Scope
The runtime instructions are user-directed example commands for specific audio files and output formats, with no hidden automation, broad file access, prompt manipulation, or destructive actions.
Install Mechanism
Installation uses the external Homebrew `openai-whisper` formula, which is expected for this CLI wrapper but means users rely on their Homebrew package source.
Credentials
No API keys, credentials, account access, broad indexing, or remote upload behavior are requested; processing is described for user-specified local audio files.
Persistence & Privilege
The skill discloses Whisper model downloads to `~/.cache/whisper` on first run; there is no evidence of background services, privilege escalation, or ongoing autonomous activity.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openai-whisper - After installation, invoke the skill by name or use
/openai-whisper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Metadata
Frequently Asked Questions
What is Openai Whisper?
Local speech-to-text with the Whisper CLI (no API key). It is an AI Agent Skill for Claude Code / OpenClaw, with 85107 downloads so far.
How do I install Openai Whisper?
Run "/install openai-whisper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openai Whisper free?
Yes, Openai Whisper is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openai Whisper support?
Openai Whisper is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openai Whisper?
It is built and maintained by Peter Steinberger (@steipete); the current version is v1.0.0.
More Skills