skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

openai-whisper-api

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

Updated Mar 7, 2026
Search Tags:#transcription#whisper#audio#curl#speech-to-text#openai api
One-click install
npx skills add https://github.com/shalevamin/Tau_agent --skill openai-whisper-api-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/openai-whisper-api
Command: npx skills add https://github.com/shalevamin/Tau_agent --skill openai-whisper-api-shalevamin

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 Whisper transcription endpoint and saves the resulting transcript to a local file. ## Core Features & Use Cases - Audio Transcription: Uploads audio files (m4a, ogg, and other supported formats) to the /v1/audio/transcriptions endpoint using curl. - Flexible Options: Supports model selection, language hints, prompt context for speaker names, and JSON or plain-text output formats. - Use Case: You have a recorded meeting saved as meeting.m4a and need a written transcript. Run the script to produce meeting.txt with the full transcription, optionally passing a prompt with participant names to improve accuracy. ## Quick Start Transcribe the audio file recording.m4a into a text transcript using the Whisper API.

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, and it uploads the file to the /v1/audio/transcriptions endpoint via curl. The transcript is saved as a .txt file next to the input by default, or to a path you specify with --out.

How to get JSON output from Whisper transcription?▼

Pass the --json flag to the script to set response_format to json instead of text. The output file then defaults to a .json extension containing the structured API response.

Does the Whisper API support language hints and custom prompts?▼

Yes, the script accepts --language to specify the audio language (e.g., en) and --prompt to provide context such as speaker names. These parameters are forwarded as form fields to the transcription endpoint.

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

The script exits if the OPENAI_API_KEY environment variable is not set. Export the key in your shell or configure it in ~/.openclaw/openclaw.json under the skill's apiKey setting before running.

What audio formats work with OpenAI transcription?▼

The script accepts any local audio file path, with examples showing m4a and ogg files. The file is uploaded as-is via multipart form data, so any format supported by the OpenAI transcriptions endpoint works.

Related Skills

Explore More Content & Communication Skills→
JYeswakJYeswak

meeting-transcribe

Transcribe recorded audio into diarized transcripts with speaker labels and timestamps.

Community
Intermediate
SugamdeolSugamdeol

openai-whisper

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

Community
Intermediate
Jin9Jin9

transcribing-media-to-minutes

Convert Thai-English meeting recordings into timestamped minutes and verbatim speaker-labeled transcripts.

Community
Advanced
abhiunixabhiunix
1

openai-whisper

Transcribes local audio to text offline using Whisper CLI without API key.

Community
Intermediate