openai-whisper

Transcribe audio locally into text using the Whisper CLI.

Updated Mar 11, 2026

Search Tags:#cli #offline #transcription #whisper #audio #local

Ready to run

npx skills add https://github.com/x402agent/NanoSolana --skill openai-whisper-x402agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/x402agent/NanoSolana/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/x402agent/NanoSolana --skill openai-whisper-x402agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio locally into text using the Whisper CLI without an API key, preserving privacy and reducing latency.

Core Features & Use Cases

Local transcription with offline processing via the Whisper CLI.
Supports model selection and output formats for transcription and translation tasks.
Privacy-first workflow: all processing happens on-device without network calls.

Quick Start

To get started, transcribe your audio locally by running whisper /path/audio.mp3 --model medium --output_format txt --output_dir .

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 locally without an API key?▼

Local audio transcription without an API key is accomplished by running the Whisper CLI directly on your device. This skill processes audio files entirely offline, ensuring privacy and reducing latency for your voice data.

Can I select different models for offline transcription?▼

Offline transcription supports selecting different Whisper models to balance accuracy and performance. You can specify models like medium during the transcription process and output formats such as txt for your resulting text files.

Does local transcription work for podcasts and meetings?▼

Local transcription works effectively for podcasts, meetings, lectures, and voice memos. It processes these audio recordings on-device without network calls, making it suitable for privacy-sensitive audio data.

How do I run the Whisper CLI to convert speech to text?▼

To convert speech to text, run the Whisper CLI command by specifying your audio file path, selecting a model, and defining the output format. The CLI processes the audio locally and outputs the text to your designated directory.

Where does the Whisper CLI cache models for transcription?▼

The Whisper CLI caches models locally in the ~/.cache/whisper directory. This local caching ensures deterministic results and avoids repeatedly downloading models for future offline transcription tasks.