skills.rest
letta-ai
letta-aiOFFICIAL
Explore all skills by this author →
Website𝕏@letta_aiGitHub

openai-whisper

Transcribe audio locally with the Whisper CLI into text or subtitle formats.

327|85|Updated Jan 29, 2026
Search Tags:#CLI#offline#transcription#whisper#privacy#local-processing#audio-to-text
One-click install
npx skills add https://github.com/letta-ai/lettabot --skill openai-whisper-letta-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/letta-ai/lettabot/tree/main/.skills/openai-whisper
Command: npx skills add https://github.com/letta-ai/lettabot --skill openai-whisper-letta-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables offline transcription of audio by using the Whisper CLI, without requiring API keys or cloud services.

Core Features & Use Cases

  • Local, on-device transcription of audio files for privacy-sensitive workflows.
  • Supports various Whisper models and outputs plain text or subtitle formats.
  • Simple CLI integration for scripts and pipelines (e.g., meetings, lectures, podcasts).

Quick Start

whisper /path/audio.mp3 --model medium --output_format txt --output_dir . whisper /path/audio.m4a --task translate --output_format srt

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 using cloud APIs?▼

You can transcribe audio to text offline by running the Whisper CLI locally on your device, ensuring privacy for sensitive audio files without needing external API keys or internet access.

Can I generate SRT subtitles from an audio file using local processing?▼

Yes, local processing with the Whisper CLI supports generating SRT subtitle formats from audio files, allowing you to create subtitles entirely on-device for videos or podcasts.

Does offline transcription with Whisper require an internet connection or API keys?▼

Offline transcription with Whisper requires neither an internet connection nor API keys, as the speech-to-text processing runs entirely on-device using locally installed binaries and models.

What is the best way to transcribe interviews privately on my own machine?▼

The best way to transcribe interviews privately is using local Whisper CLI transcription, which processes the audio entirely on your machine to maintain data confidentiality.

How do I translate an audio recording to English text locally?▼

You can translate audio to English text locally by executing the Whisper CLI with the translate task, processing the audio file entirely on-device without cloud dependency.

What limitations should I expect when running speech-to-text models on a local device?▼

Running speech-to-text models locally requires having Whisper binaries installed and selecting an appropriate model, with performance heavily dependent on your device's available compute resources.

Related Skills

Explore More Data & Analytics Skills→
coltonbattscoltonbatts

openai-whisper

Transcribe and translate local audio files using the OpenAI 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
LuisvelMarketerLuisvelMarketer
1

openai-whisper

Transcribe audio files locally using the Whisper CLI.

Community
Intermediate
p-sree-sai-pavanp-sree-sai-pavan
5

openai-whisper

Transcribe audio locally using the Whisper CLI without API keys.

Community
Intermediate