Does this skill require an OpenAI API key?

No, this skill uses the local Whisper CLI, which processes audio directly on your machine without requiring an external API key or internet connection for transcription.

Where are the Whisper models stored?

Models are automatically downloaded to and cached in the ~/.cache/whisper directory on your first run.

Which audio formats are supported?

It supports common audio formats like MP3, M4A, WAV, and others supported by the underlying Whisper and FFmpeg engine.

How do I install the required dependencies?

The skill can be configured via Homebrew on macOS using 'brew install openai-whisper' to ensure the 'whisper' binary is available in your path.

Can I use this for translating foreign languages?

Yes, the skill supports the translate task which can transcribe foreign language audio and translate it into English text automatically.

OpenAI Whisper CLI

Name: OpenAI Whisper CLI
Author: HarleyCoops

byHarleyCoops

データサイエンスとML

Enables high-accuracy local speech-to-text transcription and translation without requiring external API keys.

概要

The OpenAI Whisper skill empowers Claude to interact with local audio files directly through the Whisper command-line interface. It allows users to transcribe recordings into various formats like TXT or SRT and translate foreign language audio into English, all processed on the local machine for maximum privacy and cost-efficiency. This skill is ideal for developers and content creators who need reliable, offline audio-to-text capabilities integrated within their AI-driven workflow without the latency or costs associated with cloud services.

主な機能

Built-in translation capabilities for converting foreign audio to English.
0 GitHub stars
Local audio-to-text transcription for maximum privacy and data security.
Support for multiple output formats including TXT and SRT subtitles.
Configurable model selection to balance processing speed and transcription accuracy.
Zero-cost processing by utilizing local hardware instead of paid API keys.

ユースケース

Generating subtitles for video content or tutorials locally.
Translating foreign language audio files into English text summaries.
Transcribing meeting recordings or voice notes into searchable text documentation.

概要

主な機能

Built-in translation capabilities for converting foreign audio to English.
0 GitHub stars
Local audio-to-text transcription for maximum privacy and data security.
Support for multiple output formats including TXT and SRT subtitles.
Configurable model selection to balance processing speed and transcription accuracy.
Zero-cost processing by utilizing local hardware instead of paid API keys.

ユースケース

Generating subtitles for video content or tutorials locally.
Translating foreign language audio files into English text summaries.
Transcribing meeting recordings or voice notes into searchable text documentation.