stt-config

Read, update, validate, and enumerate speech-to-text models for Whisper and gateway routing.

6|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Acosmi/CrabClaw --skill stt-config
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stt-config
Source: https://github.com/Acosmi/CrabClaw/tree/main/docs/skills/tools/system/stt-config
Command: npx skills add https://github.com/Acosmi/CrabClaw --skill stt-config

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the lifecycle of STT configurations: reading current settings, updating models, validating connectivity, and enumerating available models across providers. This reduces manual configuration drift and speeds up deployment of new speech-to-text capabilities.

Core Features & Use Cases

  • Read and display current STT configurations and base hashes.
  • Update models, switch providers, and validate with test actions.
  • Enumerate available models per provider to compare options.

Quick Start

Query the current STT configuration with get, list available models with models for a provider, then apply a set with set and verify connectivity with test.

Frequently Asked Questions about stt-config

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

FAQPage Schema
How do I manage and update speech-to-text configuration settings?

You can manage speech-to-text configuration settings by reading current settings, updating models, and validating configurations. This process requires a baseHash for updates to enforce safe workflows and prevent configuration drift.

What speech-to-text models can I use with a gateway routing setup?

You can enumerate available speech-to-text models per provider to compare options for gateway routing scenarios. This allows you to list and select models across different providers before applying configuration updates.

How do I validate speech-to-text connectivity after switching models?

You validate speech-to-text connectivity by running a test action after updating your model configuration. This verifies that your new settings are correctly applied and that the gateway or Whisper-based provider is reachable.

Does this speech-to-text configuration tool work with Whisper models?

Yes, this speech-to-text configuration tool works with Whisper-based scenarios. You can read settings, switch providers, enumerate available Whisper models, and apply validated configuration updates safely.

Why do I need a baseHash to update STT models?

A baseHash is required to update STT models to enforce safe workflows and prevent manual configuration drift. It ensures you are working from the most current configuration state before applying any model or provider changes.