openai-whisper

Transcribe audio files to text locally using the Whisper CLI.

Updated Jun 16, 2026

Search Tags:#openai #audio transcription #speech-to-text #local processing #Whisper CLI

Ready to run

npx skills add https://github.com/breakingcircuits1337/agent-skills --skill openai-whisper-breakingcircuits1337

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/breakingcircuits1337/agent-skills/tree/main/openai-whisper
Command: npx skills add https://github.com/breakingcircuits1337/agent-skills --skill openai-whisper-breakingcircuits1337

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Transcribes audio files into text without the need for an API key, enabling local speech-to-text functionality.

Core Features & Use Cases

Local Transcription: Convert audio files to text on your local machine.
No API Key Needed: Access Whisper's capabilities without using an API key.
Use Case: Ideal for situations where internet access is limited or when you want to keep your audio data private.

Quick Start

Use the whisper command to transcribe audio: whisper /path/audio.mp3 --model medium --output_format txt --output_dir ./transcriptions/

Frequently Asked Questions about openai-whisper

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

FAQPage Schema

How do I transcribe audio files to text locally without an API key?▼

Local speech-to-text transcription without an API key is achieved using the Whisper CLI, executing local command-line operations to convert audio files into text directly on your machine.

Can I use local speech-to-text processing for private audio data?▼

Yes, local speech-to-text processing is ideal for keeping audio data private. By executing command-line operations locally via the Whisper CLI, your audio files are processed entirely on your machine without external API calls.

What is the best way to run audio transcription when internet access is limited?▼

Running local speech-to-text via the Whisper CLI is the best way to transcribe audio when internet access is limited. It processes files locally without requiring external API access or continuous network connectivity.

Do I need an OpenAI API key to use Whisper for audio transcription?▼

No, you do not need an OpenAI API key for local audio transcription. This functionality uses the Whisper CLI for local processing, bypassing the need for external API authentication entirely.

How do I convert an mp3 file to text using the Whisper CLI?▼

To convert an mp3 file to text using the Whisper CLI, execute a local command specifying the audio path, model size, output format, and output directory to generate the text transcription.

Are there limitations to local audio transcription compared to API processing?▼

Local audio transcription limitations depend entirely on your machine's processing capabilities. Running the Whisper CLI locally requires sufficient hardware resources to handle the specified model sizes for speech-to-text conversion.