skills.rest
Kastalien-Research
Kastalien-ResearchOFFICIAL
Explore all skills by this author →
WebsiteGitHub

openai-whisper

Transcribe local audio to text using the Whisper CLI without an API key.

Updated Mar 23, 2026
Search Tags:#cli#offline#transcription#whisper#audio#local#speech-to-text
One-click install
npx skills add https://github.com/Kastalien-Research/kastalien-factory --skill openai-whisper-kastalien-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Kastalien-Research/kastalien-factory/tree/main/lettabot/.skills/openai-whisper
Command: npx skills add https://github.com/Kastalien-Research/kastalien-factory --skill openai-whisper-kastalien-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes speech to text locally using the Whisper CLI without requiring an API key, ensuring privacy and offline operation.

Core Features & Use Cases

  • Local transcription: convert audio to text without internet.
  • Model flexibility: choose different Whisper models for speed or accuracy.
  • Output options: produce plain text or subtitle formats like SRT.
  • Use Case: Privacy-conscious transcription of meetings, podcasts, or lectures on a personal workstation.

Quick Start

Transcribe a local audio file using whisper, e.g., 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 to text locally without an API key?▼

You can transcribe audio to text locally without an API key by running the Whisper CLI on your personal machine. This approach ensures privacy and offline operation for transcribing meetings, podcasts, or lectures.

Can I generate SRT subtitle files from audio using offline transcription?▼

Yes, you can generate SRT subtitle files from audio using offline transcription. By configuring the output format with the Whisper CLI, you can produce plain text or subtitle files like SRT from your local audio recordings.

Do I need an internet connection to run Whisper for speech-to-text?▼

No, you do not need an internet connection to run Whisper for speech-to-text. The transcription process runs entirely locally using the Whisper CLI binary, ensuring privacy and offline operation without requiring an API key.

How do I choose different Whisper models for audio transcription?▼

You can choose different Whisper models for audio transcription by using the model selection option in the Whisper CLI. This allows you to select models that prioritize either speed or accuracy when converting your local audio files to text.

What are the limitations of local transcription with the Whisper CLI?▼

A limitation of local transcription with the Whisper CLI is that it requires the Whisper binary to be installed and available on your PATH. Additionally, selecting larger models for higher accuracy will require more local computing resources on your personal workstation.

Related Skills

Explore More Software Engineering Skills→
ybsaybsa
3

openai-whisper

Transcribe local audio files to text using the Whisper CLI.

Community
Basic
NanmiCoderNanmiCoder
60

srt-to-structured-data

Parses SRT subtitle files into structured JSON with optional statistics and text output.

Community
Intermediate
steipetesteipete
385.7k

openai-whisper

Transcribe local audio files to text or subtitles using the Whisper CLI.

Community
Intermediate
JiayueMeng128JiayueMeng128

openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

Community
Intermediate