skills.rest
AmirulAndalib
AmirulAndalibCOMMUNITY
Explore all skills by this author →
GitHub

openai-whisper-api

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

Updated Jun 19, 2026
Search Tags:#transcription#whisper#audio#openai#curl#speech-to-text#diarization
One-click install
npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill openai-whisper-api-amirulandalib
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/AmirulAndalib/Vilvona-AI/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/AmirulAndalib/Vilvona-AI --skill openai-whisper-api-amirulandalib

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Converting audio recordings like voice memos, meetings, and interviews into text requires manual transcription or complex SDK setup. This Skill transcribes audio files through the OpenAI /v1/audio/transcriptions endpoint with a single shell command. ## Core Features & Use Cases - Multiple Transcription Models: Choose between gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-transcribe-diarize for speaker labels, or whisper-1. - Flexible Output: Produces plain text transcripts by default or full JSON responses, with automatic speaker-labeled line formatting for diarized output. - Language and Prompt Hints: Pass a language code or prompt to guide recognition of names and terminology. - Use Case: Record a meeting as an m4a file, then run the transcribe script with the diarize model to get a speaker-attributed transcript saved next to the audio file. ## Quick Start Transcribe the attached audio file meeting.m4a to text using the OpenAI transcription API with the default gpt-4o-transcribe model.

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 API?▼

Run the transcribe.sh script with your audio file path, for example transcribe.sh audio.m4a. It uploads the file to /v1/audio/transcriptions with the gpt-4o-transcribe model and writes the transcript to a .txt file next to the input.

How to get speaker labels in OpenAI transcription?▼

Use the gpt-4o-transcribe-diarize model with the --model flag. The script sends chunking_strategy=auto and formats the diarized JSON segments into speaker-prefixed lines. Note that --prompt is not supported with this model.

What audio formats does the OpenAI transcription API support?▼

Supported upload formats include mp3, mp4, mpeg, mpga, m4a, wav, and webm. The hosted API enforces a 25 MB upload limit per file.

Can I use a local or proxy OpenAI-compatible endpoint for transcription?▼

Yes, set the OPENAI_BASE_URL environment variable to point at an OpenAI-compatible proxy or local gateway. The script appends /audio/transcriptions to that base URL instead of api.openai.com.

Why does transcription fail with a missing API key error?▼

The script requires the OPENAI_API_KEY environment variable and exits if it is unset. Set it in your shell or configure it in the OpenClaw config file under the openai-whisper-api skill entry.

Related Skills

Explore More Software Engineering Skills→
pchemguypchemguy

transcribe

Transcribe audio files to text with optional speaker diarization using OpenAI models.

Community
Intermediate
SugamdeolSugamdeol

openai-whisper

Transcribes local audio files using the Whisper CLI without external APIs.

Community
Intermediate
hmzainjamilhmzainjamil
1

Transcription Automation

Convert audio and video recordings into transcripts, subtitles, and meeting notes.

Community
Advanced
iia-argiia-arg

use-local-whisper

Transcribe WhatsApp voice messages locally using whisper.cpp on Apple Silicon.

Community
Intermediate