whisper-stt

Convert operator speech into offline text transcription with Apple Silicon Whisper models.

Updated Jun 6, 2026
One-click install
npx skills add https://github.com/J4Joshua/manuaI --skill whisper-stt-j4joshua
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: whisper-stt
Source: https://github.com/J4Joshua/manuaI/tree/main/.agents/skills/whisper-stt
Command: npx skills add https://github.com/J4Joshua/manuaI --skill whisper-stt-j4joshua

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of converting factory operator speech into accurate text locally without relying on cloud services, enabling reliable voice interactions in offline industrial environments.

Core Features & Use Cases

  • Local Speech Transcription: Converts push-to-talk audio into text using Apple Silicon optimized Whisper backends such as mlx-whisper and faster-whisper.
  • Latency Optimization: Helps select and tune Whisper models, caching strategies, and inference settings for fast voice responses in noisy factory environments.
  • Voice Pipeline Integration: Supports connecting offline transcription with ManuAI voice workflows, LiveKit agents, retrieval systems, and local language models.

Quick Start

Use the whisper-stt skill to configure a local Whisper transcription pipeline for a push-to-talk factory operator voice assistant.

Frequently Asked Questions about whisper-stt

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

FAQPage Schema
How do I set up offline speech recognition for a push-to-talk voice assistant?

Configure offline speech recognition by deploying local Whisper backends like mlx-whisper or faster-whisper on Apple Silicon, enabling low-latency text transcription without cloud connectivity.

Can I use mlx-whisper or faster-whisper for industrial voice transcription on Apple Silicon?

Yes, local speech transcription on Apple Silicon utilizes optimized Whisper backends such as mlx-whisper and faster-whisper to convert operator speech into text for industrial voice workflows.

What is the best way to optimize Whisper latency in noisy factory environments?

Optimize Whisper latency by selecting appropriate models, configuring offline caching strategies, and tuning inference settings to ensure fast voice responses in noisy factory environments.

Does offline local speech recognition work with LiveKit agents for voice pipelines?

Offline local speech recognition integrates with voice pipelines by connecting transcription outputs to LiveKit agents, retrieval systems, and local language models for workflow automation.

When should I use offline speech recognition instead of cloud-based STT services?

Use offline speech recognition instead of cloud-based STT when reliable voice interactions are required in industrial environments lacking internet connectivity or strict data privacy constraints.