skills.rest
travis-burmaster
travis-burmasterCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

openai-whisper-api

Transcribe audio files to text via the OpenAI Whisper API using curl.

Updated Feb 16, 2026
Search Tags:#transcription#whisper#audio#curl#speech-to-text#openai api
One-click install
npx skills add https://github.com/travis-burmaster/agentbox --skill openai-whisper-api-travis-burmaster
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/travis-burmaster/agentbox/tree/main/agentfork/skills/openai-whisper-api
Command: npx skills add https://github.com/travis-burmaster/agentbox --skill openai-whisper-api-travis-burmaster

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Converting audio recordings into text manually is slow and error-prone. This Skill sends audio files directly to OpenAI's /v1/audio/transcriptions endpoint and saves the resulting transcript to a local file, removing the need to write API integration code yourself. ## Core Features & Use Cases - Audio Transcription: Upload audio files (m4a, ogg, and other supported formats) to the Whisper API and receive plain text or JSON output. - Configurable Options: Control the model, output path, language hint, and prompt context (e.g., speaker names) via command-line flags. - Use Case: You have a recorded meeting saved as meeting.m4a. Run the transcribe script to produce meeting.txt, optionally passing a prompt with participant names to improve recognition accuracy. ## Quick Start Transcribe the audio file meeting.m4a using the OpenAI Whisper API and save the transcript as a text file.

Frequently Asked Questions about openai-whisper-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe an audio file with the OpenAI Whisper API?▼

Run the transcribe.sh script with your audio file path, for example transcribe.sh /path/to/audio.m4a. The script uploads the file to the /v1/audio/transcriptions endpoint and writes the transcript to a .txt file next to the input by default.

How do I get JSON output from Whisper transcription instead of plain text?▼

Pass the --json flag to the transcribe script, which sets response_format to json. The output file then defaults to a .json extension, or you can specify a custom path with --out.

What do I need to use the OpenAI audio transcription API?▼

You need the curl binary installed and a valid OPENAI_API_KEY set as an environment variable. The key can also be configured in the openclaw.json config file under the skill's apiKey field.

Can I improve Whisper transcription accuracy for names or jargon?▼

Yes, use the --prompt flag to pass context such as speaker names or domain vocabulary, and --language to specify the audio language. These hints guide the model toward more accurate recognition.

Why does the transcription script fail with a missing key error?▼

The script exits with an error when OPENAI_API_KEY is not set in the environment. Export the variable before running the script, or configure the key in ~/.openclaw/openclaw.json.

Related Skills

Explore More Content & Communication Skills→
shalevaminshalevamin

openai-whisper-api

Transcribe audio files to text via the OpenAI Audio Transcriptions API.

Community
Basic
duylinhdang1998duylinhdang1998

nlp-expert

Build NLP pipelines for preprocessing, classification, embedding generation, and retrieval.

Community
Intermediate
JigsawStackJigsawStack
4

speech-to-text

Convert spoken audio into searchable transcripts with timestamps and speaker labels.

Official
Intermediate
framerslabframerslab

vosk

Transcribe audio files to text offline using the Vosk library.

Official
Intermediate