openai-whisper

Transcribe audio files locally using the Whisper CLI.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill openai-whisper-balic-ai-ml-r-d-resources
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents/tree/main/packages/skills/skills/openai-whisper
Command: npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill openai-whisper-balic-ai-ml-r-d-resources

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local speech-to-text conversion for audio files without relying on external APIs, enabling offline privacy-preserving transcription.

Core Features & Use Cases

  • Transcription: convert audio to text using the Whisper model locally.
  • Subtitles & Captions: generate SRT/VTT captions and translations from audio/video inputs.
  • Flexible formats & offline: works with mp3, m4a, wav; no API key required; model selection affects speed/accuracy.

Quick Start

Transcribe an input audio file locally using whisper to generate a transcript or subtitle file.

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 to text offline without an API key?

You can transcribe audio to text offline by running the Whisper CLI locally to process mp3, m4a, or wav files into text transcripts without requiring any external API keys.

Can I generate SRT or VTT subtitles from an audio file locally?

Yes, generating SRT or VTT subtitles locally is supported by running the Whisper CLI to convert your audio or video inputs into formatted caption files entirely offline.

Does offline speech-to-text transcription work with wav and m4a files?

Offline speech-to-text transcription supports wav and m4a files directly, processing these audio formats through the configured local Whisper models to produce accurate text outputs.

What is the best way to transcribe private audio files without cloud APIs?

The best way to transcribe private audio files without cloud APIs is using local offline transcription with the Whisper CLI, ensuring data privacy by processing conversations and spoken language entirely on your machine.

How does model selection affect offline transcription speed and accuracy?

Model selection directly affects offline transcription speed and accuracy, allowing you to choose different configured Whisper models via the CLI to balance processing time against text output precision.

Can I translate spoken language to text without an internet connection?

Yes, you can translate spoken language to text without an internet connection by using the local Whisper CLI to process audio inputs offline and generate translated text transcripts.