skills.rest
deepgram
deepgramOFFICIAL
Explore all skills by this author →
WebsiteGitHub

openai-whisper

Convert audio files to text locally using the Whisper CLI.

23|10|Updated Feb 9, 2026
Search Tags:#transcription#audio processing#speech-to-text#local conversion#Whisper CLI
One-click install
npx skills add https://github.com/deepgram/dglabs-deepclaw --skill openai-whisper-deepgram
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/deepgram/dglabs-deepclaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/deepgram/dglabs-deepclaw --skill openai-whisper-deepgram

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert spoken words into text using local speech-to-text technology, eliminating the need for an API key.

Core Features & Use Cases

  • Local Speech-to-Text: Use the Whisper CLI for audio transcription without the need for an external API.
  • No API Key Required: Ideal for those who prefer not to use an API for privacy reasons.
  • Use Case: Imagine you have an interview recording and want to convert it to text without an internet connection.

Quick Start

Run the whisper command on your audio file: 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?▼

Local audio transcription to text without an API key is achieved by running the Whisper CLI on your machine, converting spoken words directly on your device. This eliminates the need for external services and preserves privacy.

Can I convert speech to text without an internet connection?▼

Yes, speech-to-text conversion works without an internet connection using the local Whisper CLI. It processes audio files entirely on your device, making it ideal for offline environments and immediate processing.

How do I use the Whisper CLI for speech-to-text conversion?▼

To use the Whisper CLI for speech-to-text conversion, run the whisper command targeting your audio file, specify the model size, and define the output format and directory to generate the text transcription.

Does local audio processing offer better privacy than cloud transcription?▼

Local audio processing offers better privacy than cloud transcription because it keeps your audio data entirely on your device. It eliminates the need to upload sensitive recordings to external API servers.

What are the limitations of using local speech-to-text conversion?▼

Limitations of local speech-to-text conversion include relying entirely on your device's processing power for latency and model execution. The CLI processes audio without cloud support, so performance depends on local hardware capabilities.

Related Skills

Explore More Software Engineering Skills→
nuno7lopesnuno7lopes

openai-whisper

Transcribe audio files to text using the local Whisper CLI.

Community
Basic
Hawksight-AIHawksight-AI
2.9k

extract

Extract entities, relations, events, and triplets from text into Markdown tables.

Official
Intermediate
digresik-techdigresik-tech
1

ASR

Transcribe audio files and base64 audio into text using the z-ai-web-dev-sdk.

Community
Intermediate
framerslabframerslab

vosk

Transcribe audio files to text offline using the Vosk library.

Official
Intermediate