use-local-whisper

Switch voice transcription from the OpenAI Whisper API to local whisper.cpp.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/E01N/ClawOutreach --skill use-local-whisper-e01n
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: use-local-whisper
Source: https://github.com/E01N/ClawOutreach/tree/main/nanoclaw/.claude/skills/use-local-whisper
Command: npx skills add https://github.com/E01N/ClawOutreach --skill use-local-whisper-e01n

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Historically, on-device voice transcription relied on cloud-based APIs, exposing data and incurring latency; this skill switches to local whisper.cpp to run entirely on-device, with no API key or network requirement.

Core Features & Use Cases

  • Switches transcription from the OpenAI Whisper API to local whisper.cpp for on-device processing
  • WhatsApp channel support with pre-applied voice-transcription skill
  • Works offline after dependencies are installed, enabling privacy-preserving transcription

Quick Start

Apply this skill to switch transcription to local whisper.cpp for WhatsApp, ensuring the voice-transcription skill is already applied.

Frequently Asked Questions about use-local-whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe WhatsApp voice messages locally on macOS?

To transcribe WhatsApp voice messages locally, you can use on-device whisper.cpp processing on macOS Apple Silicon, which switches transcription entirely offline without requiring an OpenAI API key.

Do I need an OpenAI API key for on-device whisper.cpp transcription?

No, you do not need an OpenAI API key for on-device whisper.cpp transcription, as it switches processing from the cloud API to local whisper-cli, operating entirely offline.

What dependencies are required to run local whisper.cpp for WhatsApp transcription?

Local whisper.cpp transcription requires whisper-cpp, ffmpeg, and a GGML model installed, alongside a pre-applied voice-transcription skill on macOS Apple Silicon.

Can I use whisper-cli for offline voice transcription on Apple Silicon?

Yes, you can use whisper-cli for offline voice transcription on Apple Silicon by applying this skill to update code paths, provided the voice-transcription skill is applied first.

How does local whisper.cpp transcription compare to the OpenAI Whisper API?

Local whisper.cpp transcription replaces the OpenAI Whisper API by running entirely on-device, which prevents data exposure and removes network latency requirements.

Why does my local whisper.cpp transcription require ffmpeg?

Local whisper.cpp transcription requires ffmpeg to process and convert WhatsApp audio formats, ensuring the voice messages are compatible with whisper-cli input requirements.