skills.rest
TobiasWooldridge
TobiasWooldridgeCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

wavecap-config

View and edit WaveCap config.yaml settings for Whisper, LLM, and streams.

Updated Aug 23, 2026
Search Tags:#llm#configuration#transcription#whisper#settings#wavecap
One-click install
npx skills add https://github.com/TobiasWooldridge/WaveCap --skill wavecap-config
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wavecap-config
Source: https://github.com/TobiasWooldridge/WaveCap/tree/main/.claude/skills/wavecap-config
Command: npx skills add https://github.com/TobiasWooldridge/WaveCap --skill wavecap-config

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill allows users to easily view and modify the configuration settings for the WaveCap real-time transcription application, enabling customization of transcription models, LLM corrections, and stream definitions.

Core Features & Use Cases

  • View Configuration: Inspect current settings for Whisper, LLM correction, UI, and streams.
  • Modify Settings: Update parameters like Whisper models, LLM configurations, and stream details.
  • Use Case: A user wants to switch to a faster Whisper model to reduce transcription latency. They can use this skill to view the current Whisper settings, change the model parameter in config.yaml, and then restart the backend.

Quick Start

Use the wavecap-config skill to view the Whisper settings in the config.yaml file.

Frequently Asked Questions about wavecap-config

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

FAQPage Schema
How do I configure Whisper transcription settings for real-time audio streams?▼

You can configure Whisper transcription settings by viewing and editing the `config.yaml` file to update parameters like the transcription model, then restart the backend to apply the changes.

Can I use LLM correction models to improve transcription accuracy in WaveCap?▼

Yes, WaveCap supports LLM correction models. You can view and modify LLM configurations and correction terms directly within the `config.yaml` file to enhance transcription accuracy.

What's the best way to switch to a faster Whisper model to reduce transcription latency?▼

The best way to reduce latency is to view the current Whisper settings in `config.yaml`, change the `model` parameter to a faster option, and then restart the backend to apply the update.

How do I update stream definitions for real-time transcription?▼

You can update stream definitions by editing the `config.yaml` file to add or modify stream details, then restart the backend to ensure the new stream configurations take effect.

Do I need direct file access to modify WaveCap application configuration settings?▼

Yes, direct file access and command-line interaction are required to view and update the `config.yaml` file, as well as to perform backend restarts for applying operational adjustments.

Why does my WaveCap configuration not update after changing Whisper parameters?▼

Configuration changes to Whisper parameters require a backend restart to take effect. Ensure you restart the backend service after saving updates to the `config.yaml` file.

Related Skills

Explore More Software Engineering Skills→
jasonkneenjasonkneen
471

obsidian

Read, search, create, and edit notes in an Obsidian vault.

Community
Intermediate
LIMITLESS-LONGEVITYLIMITLESS-LONGEVITY

use-local-whisper

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

Official
Intermediate
fishyerfishyer
1

ASR

Transcribe base64 encoded audio files into text using the z-ai-web-dev-sdk.

Community
Intermediate
CRAG666CRAG666
46

markitdown

Convert common document types into Markdown for LLM ingestion.

Community
Advanced