skills.rest
clsandoval
clsandovalCOMMUNITY
Explore all skills by this author →
GitHub

use-local-whisper

Transcribe WhatsApp voice messages locally using whisper.cpp on Apple Silicon.

Updated Jan 19, 2026
Search Tags:#transcription#whatsapp#ffmpeg#on-device#whisper.cpp#local-transcription#voice-processing
One-click install
npx skills add https://github.com/clsandoval/monorepo --skill use-local-whisper-clsandoval
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: use-local-whisper
Source: https://github.com/clsandoval/monorepo/tree/main/automations/nanoclaw/.claude/skills/use-local-whisper
Command: npx skills add https://github.com/clsandoval/monorepo --skill use-local-whisper-clsandoval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes voice messages locally by switching from the OpenAI Whisper API to a local whisper.cpp backend, enabling on-device transcription without network access or API keys.

Core Features & Use Cases

  • On-device transcription for WhatsApp voice messages using whisper.cpp
  • Requires Apple Silicon Macs and the whisper-cpp and ffmpeg toolchain
  • Works with existing voice-transcription workflows and preserves message integrity for further processing

Quick Start

Apply the voice-transcription skill for WhatsApp and ensure whisper-cpp and ffmpeg are installed, then test transcription on a voice message.

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 without using the OpenAI Whisper API?▼

Local transcription of WhatsApp voice messages is achieved by replacing the OpenAI Whisper API with a local whisper.cpp backend. This on-device processing downloads audio, converts it to 16 kHz mono WAV, and transcribes locally without API keys or network calls.

Can I run on-device voice transcription on macOS without an internet connection?▼

Yes, on-device voice transcription runs entirely offline on macOS Apple Silicon. It processes WhatsApp voice messages locally using whisper-cli and a local model, strictly avoiding any network calls or API keys during transcription.

What dependencies are needed to set up local whisper.cpp transcription for WhatsApp?▼

Setting up local whisper.cpp transcription requires macOS Apple Silicon with the whisper-cpp and ffmpeg toolchain installed. You must also ensure the whisper-cli is used and the model is placed at data/models/ggml-base.bin.

Does local transcription with whisper.cpp work on Windows or Linux?▼

Local transcription with whisper.cpp is explicitly designed for macOS with Apple Silicon. The metadata does not support compatibility for Windows or Linux environments, making it a strictly Apple Silicon on-device solution.

Why does local voice processing require converting audio to 16 kHz mono WAV?▼

Converting audio to 16 kHz mono WAV is required for local voice processing because the whisper.cpp transcription engine expects this specific format. The ffmpeg toolchain handles this conversion before the local whisper-cli processes the file.

Related Skills

Explore More Software Engineering Skills→
DingyangLyuDingyangLyu
85

use-local-whisper

Replace cloud-based voice transcription with local whisper.cpp processing on macOS Apple Silicon.

Community
Advanced
reedmayhew18reedmayhew18
23

oc-voice

Transcribe voice chat messages with Whisper and route text downstream.

Community
Intermediate
clsandovalclsandoval

add-voice-transcription

Transcribe WhatsApp voice notes to text using OpenAI Whisper.

Community
Advanced
sbussosbusso
189

use-local-whisper

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

Community
Intermediate