skills.rest
srgaba
srgabaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

openai-whisper-api

Transcribe audio files to text via the OpenAI Whisper transcriptions API.

Updated Mar 30, 2026
Search Tags:#transcription#whisper#audio#curl#speech-to-text#openai api
One-click install
npx skills add https://github.com/srgaba/open-claw --skill openai-whisper-api-srgaba
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/srgaba/open-claw/tree/main/project/skills/openai-whisper-api
Command: npx skills add https://github.com/srgaba/open-claw --skill openai-whisper-api-srgaba

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, and 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 to OpenAI's /v1/audio/transcriptions endpoint and saves the resulting transcript automatically. ## Core Features & Use Cases - Audio Transcription: Transcribe audio files (m4a, ogg, and other supported formats) using the whisper-1 model via a simple curl-based script. - Flexible Options: Specify language, prompt hints (e.g., speaker names), output path, and JSON or plain-text response format. - Proxy Support: Set OPENAI_BASE_URL to route requests through an OpenAI-compatible proxy or local gateway. - Use Case: You have a recorded meeting saved as meeting.m4a. Run the transcribe script to produce meeting.txt with the full transcript, optionally passing a prompt with attendee names to improve recognition. ## Quick Start Transcribe the audio file meeting.m4a to text using the OpenAI Whisper API and save the transcript next to the original 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. It sends the file to the /v1/audio/transcriptions endpoint with the whisper-1 model and writes the transcript to a .txt file next to the input.

How to get JSON output from Whisper transcription?▼

Pass the --json flag to the transcribe script, which sets response_format to json and saves the output as a .json file instead of plain text. You can also set a custom output path with --out.

Can I use a local or proxy Whisper API endpoint?▼

Yes, set the OPENAI_BASE_URL environment variable to any OpenAI-compatible endpoint, such as http://127.0.0.1:51805/v1. The script strips trailing slashes and sends requests to that base URL instead of api.openai.com.

Why does transcription fail with Missing OPENAI_API_KEY?▼

The script requires the OPENAI_API_KEY environment variable to authenticate with the API. Export it in your shell or configure it in ~/.openclaw/openclaw.json under the skill's apiKey setting before running the script.

How do I improve transcription accuracy for names or jargon?▼

Use the --prompt flag to pass a hint string, such as speaker names or domain vocabulary, for example --prompt "Speaker names: Peter, Daniel". You can also set --language to specify the audio language explicitly.

Related Skills

Explore More Content & Communication Skills→
shalevaminshalevamin

openai-whisper-api

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

Community
Basic
mosaxivmosaxiv
328

summarize

Summarize text from URLs, transcripts, and local files with configurable output length.

Community
Intermediate
JigsawStackJigsawStack
4

speech-to-text

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

Official
Intermediate
framerslabframerslab

streaming-stt-whisper

Transcribe live speech in real time using the OpenAI Whisper API.

Official
Intermediate