← Back to Skills Marketplace
Openai Whisper Api
by
Peter Steinberger
· GitHub ↗
· v1.0.0
27611
Downloads
52
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openai-whisper-api
Description
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Usage Guidance
Install only if you are comfortable sending the selected audio files to OpenAI for transcription. Avoid using it for confidential, regulated, or third-party recordings without authorization, and choose output paths carefully so transcripts do not overwrite important files.
Capability Analysis
Type: OpenClaw Skill
Name: openai-whisper-api
Version: 1.0.0
The skill is classified as suspicious due to a local file write vulnerability in `scripts/transcribe.sh`. The `--out` parameter allows the user to specify an arbitrary file path for the transcription output, which could lead to overwriting sensitive files (e.g., configuration files, startup scripts) if the user has write permissions to those locations. While the skill's primary purpose is legitimate, this lack of output path validation presents a significant security risk, potentially enabling data corruption or persistence if exploited by a malicious actor.
Capability Assessment
Purpose & Capability
The network upload, OpenAI API use, local audio read, and transcript file write are coherent with an OpenAI Whisper API transcription skill.
Instruction Scope
The supplied scanner context indicates the docs and runtime help may not clearly warn that audio contents are uploaded to OpenAI; that is important user-facing disclosure but still aligned with the stated API-based purpose.
Install Mechanism
No evidence was supplied or found of hidden installers, dependency confusion, automatic background setup, or unrelated package installation.
Credentials
Using an OpenAI API key, network access, and local input/output files is proportionate for cloud transcription, but users should treat audio as potentially sensitive before uploading it.
Persistence & Privilege
The reported --out option can write to a user-chosen path, including overwriting a writable file, but this is a normal user-directed output feature and no evidence shows automatic persistence or hidden privileged writes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openai-whisper-api - After installation, invoke the skill by name or use
/openai-whisper-api - 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 Api?
Transcribe audio via OpenAI Audio Transcriptions API (Whisper). It is an AI Agent Skill for Claude Code / OpenClaw, with 27611 downloads so far.
How do I install Openai Whisper Api?
Run "/install openai-whisper-api" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openai Whisper Api free?
Yes, Openai Whisper Api is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openai Whisper Api support?
Openai Whisper Api is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openai Whisper Api?
It is built and maintained by Peter Steinberger (@steipete); the current version is v1.0.0.
More Skills