skills.rest
sbusso
sbussoCOMMUNITY
Explore all skills by this author →
Website𝕏@sbussoGitHub

use-local-whisper

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

189|60|Updated Mar 22, 2026
Search Tags:#transcription#macos#audio#whatsapp#ffmpeg#on-device#whisper.cpp
One-click install
npx skills add https://github.com/sbusso/claudeclaw --skill use-local-whisper-sbusso
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: use-local-whisper
Source: https://github.com/sbusso/claudeclaw/tree/main/skills/use-local-whisper
Command: npx skills add https://github.com/sbusso/claudeclaw --skill use-local-whisper-sbusso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Switches voice transcription from the OpenAI Whisper API to local whisper.cpp, enabling on-device transcription with no API keys or network access.

Core Features & Use Cases

  • WhatsApp-only support for now, with on-device transcription on macOS Apple Silicon.
  • Runs entirely offline using whisper.cpp and ffmpeg, avoiding external API costs.
  • Depends on the voice-transcription skill being applied first and requires a GGML model file in data/models/.

Quick Start

Install whisper-cpp and ffmpeg via Homebrew, ensure a GGML model is present in data/models, and apply the voice-transcription skill to enable local transcription.

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 audio locally on macOS Apple Silicon without an API?▼

Local audio transcription on macOS Apple Silicon uses whisper.cpp to process WhatsApp voice messages offline, avoiding external API costs. It requires the voice-transcription skill, whisper-cli, and ffmpeg to function independently without network access.

What do I need to set up whisper.cpp for offline transcription?▼

Offline transcription setup requires installing whisper-cpp and ffmpeg via Homebrew, placing a GGML model file in data/models, and applying the voice-transcription skill beforehand to enable local processing.

Can I use local whisper.cpp instead of the OpenAI Whisper API for voice transcription?▼

Yes, this approach switches voice transcription from the OpenAI Whisper API to local whisper.cpp, allowing on-device processing entirely offline. It substitutes the external API with a local GGML model run through whisper-cli.

Does WhatsApp voice transcription work without network access on macOS?▼

Yes, WhatsApp voice transcription runs entirely offline on macOS Apple Silicon. By leveraging local whisper.cpp and ffmpeg, it processes audio files without requiring network access or API keys.

What are the limitations of using whisper.cpp for local audio transcription?▼

Current limitations include WhatsApp-only support restricted to macOS Apple Silicon devices. Users must also manually manage a GGML model in data/models and ensure ffmpeg and whisper-cli are properly installed.

Related Skills

Explore More Software Engineering Skills→
spyqsspyqs

use-local-whisper

Switch WhatsApp transcription from the Whisper API to local whisper.cpp.

Community
Intermediate
theowenyoungtheowenyoung

add-voice-transcription

Transcribe WhatsApp voice messages into readable text for agents.

Community
Intermediate
guoqiaoguoqiao

mlx-tts

Generate speech audio from text locally on macOS Apple Silicon using MLX models.

Community
Intermediate
qwibitaiqwibitai
10

use-local-whisper

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

Official
Intermediate