← Back to Skills Marketplace
mohdalhashemi98-hue

MH openai-whisper-api

cross-platform ✓ Security Clean
479
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mh-openai-whisper-api
Description
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
README (SKILL.md)

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

  • Model: whisper-1
  • Output: \x3Cinput>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key

Set OPENAI_API_KEY, or configure it in ~/.openclaw/openclaw.json:

{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}
Usage Guidance
This skill simply uploads a local audio file to OpenAI's transcription endpoint using curl and your OPENAI_API_KEY. Before installing, consider: (1) Privacy — your audio is sent to OpenAI; don't upload sensitive audio unless you're comfortable with OpenAI's handling and retention policies. (2) Keep your OPENAI_API_KEY secret and revoke it if compromised. (3) The SKILL.md mentions storing a key in ~/.openclaw/openclaw.json for convenience, but the script only reads the OPENAI_API_KEY environment variable — ensure you understand how your platform provides keys. (4) Verify network access to api.openai.com and that curl is the expected binary on your system. The included shell script is short, readable, and not obfuscated; no other endpoints or hidden behaviors were found.
Capability Analysis
Type: OpenClaw Skill Name: mh-openai-whisper-api Version: 1.0.0 The skill bundle is designed to transcribe audio using the OpenAI Whisper API, a legitimate function. The `SKILL.md` provides clear instructions and examples without any malicious prompt injection attempts. The `scripts/transcribe.sh` script correctly handles user input by properly quoting variables (`"$in"`, `"$out"`, `"${model}"`, etc.) when used in shell commands and by passing parameters to `curl` as form fields (`-F`), which prevents shell injection. There is no evidence of data exfiltration beyond the stated purpose (sending audio to OpenAI), persistence, obfuscation, or other malicious behaviors.
Capability Assessment
Purpose & Capability
Name/description, required binary (curl), required env var (OPENAI_API_KEY), and provided script all align with a Whisper transcription client that calls OpenAI's audio/transcriptions API.
Instruction Scope
SKILL.md and the script only instruct uploading a provided audio file to api.openai.com and writing the response to a local file. The README suggests an alternate place to store the API key (~/.openclaw/openclaw.json) for user convenience, but the script itself only reads OPENAI_API_KEY from the environment. There are no instructions to read arbitrary system files or send data to other endpoints.
Install Mechanism
Instruction-only skill with no install spec and a small helper script; no downloads or extraction steps. This is low-risk from an install perspective.
Credentials
Only OPENAI_API_KEY is required, which is appropriate for calling OpenAI's API. No other credentials, system config paths, or unrelated environment variables are requested. The key is used directly in an Authorization header to call OpenAI — expected behavior.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system privileges. It does not modify other skills or system configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install mh-openai-whisper-api
  3. After installation, invoke the skill by name or use /mh-openai-whisper-api
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Priority upload batch
Metadata
Slug mh-openai-whisper-api
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is MH openai-whisper-api?

Transcribe audio via OpenAI Audio Transcriptions API (Whisper). It is an AI Agent Skill for Claude Code / OpenClaw, with 479 downloads so far.

How do I install MH openai-whisper-api?

Run "/install mh-openai-whisper-api" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is MH openai-whisper-api free?

Yes, MH openai-whisper-api is completely free (open-source). You can download, install and use it at no cost.

Which platforms does MH openai-whisper-api support?

MH openai-whisper-api is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created MH openai-whisper-api?

It is built and maintained by mohdalhashemi98-hue (@mohdalhashemi98-hue); the current version is v1.0.0.

💬 Comments