This handles local speech-to-text using Faster Whisper, built specifically for the JARVIS voice assistant. It's a complete TDD-based implementation that prioritizes privacy (processes locally, deletes audio immediately) and real-time performance with VAD filtering and streaming transcription. The guide walks through model selection from tiny to large-v3, includes concrete latency targets (under 300ms for short audio), and shows optimization patterns like int8 quantization for CPU and chunked processing to avoid waiting for complete recordings. The medium risk rating reflects audio processing and privacy concerns, but the approach is solid if you need offline voice recognition without cloud dependencies.

skills.sh installs
282
GitHub stars
48
last updated
Aug 21, 2026

Install

$ npx -y skills add martinholovsky/claude-skills-generator --skill speech-to-text --agent claude-code

Installs into .claude/skills of the current project.

Files

Speech-to-Text Skill

File Organization: Split structure. See references/ for detailed implementations.

1. Overview

Risk Level: MEDIUM - Processes audio input, potential privacy concerns, resource-intensive

You are an expert in speech-to-text systems with deep expertise in Faster Whisper, audio processing, and transcription optimization. Your mastery spans model selection, audio preprocessing, real-time transcription, and privacy protection for voice data.

You excel at:

  • Faster Whisper deployment and optimization
  • Audio preprocessing and noise reduction
  • Real-time streaming transcription
  • Privacy-preserving voice processing
  • Multi-language and accent handling

Primary Use Cases:

  • JARVIS voice command recognition
  • Real-time transcription with low latency
  • Offline speech recognition (no cloud dependency)
  • Multi-language support for accessibility

2. Core Principles

Sponsors

Details

Repository
github.com/martinholovsky/claude-skills-generator
Categories
Automation & Workflows, Generative Media, Video & Audio Editing
First seen
Jun 3, 2026

More from martinholovsky/claude-skills-generator

All 50
1martinholovsky avatarsurrealdb-expertmartinholovsky/claude-skills-generatorExpert SurrealDB developer specializing in multi-model database design, graph relations, document storage, SurrealQL queries, row-level security, and real-time 275skills.sh installs
2martinholovsky avatargraph-database-expertmartinholovsky/claude-skills-generatorExpert in graph database design and development with deep knowledge of graph modeling, traversals, query optimization, and relationship patterns. Specializes in270skills.sh installs
3martinholovsky avatarwebsocketmartinholovsky/claude-skills-generatorReal-time bidirectional communication with security focus on CSWSH prevention, authentication, and message validation269skills.sh installs
4martinholovsky avatarrustmartinholovsky/claude-skills-generatorSystems programming expertise for Tauri desktop application backend development with memory safety and performance optimization266skills.sh installs
5martinholovsky avatarfastapimartinholovsky/claude-skills-generatorREST API and WebSocket development with FastAPI emphasizing security, performance, and async patterns264skills.sh installs
6martinholovsky avatarasync-programmingmartinholovsky/claude-skills-generatorConcurrent operations with asyncio and Tokio, focusing on race condition prevention, resource safety, and performance258skills.sh installs