stt-service

Manage Speech-to-Text service initialization, recording, transcription, and result forwarding.

Updated Jan 27, 2026
One-click install
npx skills add https://github.com/Aliisa-yt/twitchbot --skill stt-service-aliisa-yt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stt-service
Source: https://github.com/Aliisa-yt/twitchbot/tree/main/.github/skills/stt-service
Command: npx skills add https://github.com/Aliisa-yt/twitchbot --skill stt-service-aliisa-yt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a robust Speech-to-Text (STT) pipeline, enabling real-time transcription of audio input for integration with other services like TTS or chat display.

Core Features & Use Cases

  • STT Pipeline Management: Initializes and manages the STT engine, including recording, processing, and forwarding transcribed text.
  • Runtime Control: Allows for dynamic adjustments like muting and threshold settings.
  • Resilience: Designed to handle microphone device loss and recovery gracefully, ensuring continuous operation.
  • Use Case: Integrate live speech recognition into a Twitch bot to transcribe viewer messages or spoken commands in real-time, making the bot more interactive.

Quick Start

Initialize the STT service to begin transcribing audio input.

Frequently Asked Questions about stt-service

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

FAQPage Schema
How do I add real-time speech-to-text transcription to a Twitch bot?

Real-time speech-to-text for Twitch bots is enabled by initializing an STT pipeline that manages audio recording, processes transcription, and forwards text results to integrated services. You can use this to transcribe spoken commands or viewer messages live.

Can I dynamically mute audio or adjust thresholds during live transcription processing?

Yes, live transcription processing supports runtime controls for muting audio input and adjusting threshold settings dynamically. This allows you to manage the speech-to-text pipeline continuously without interrupting the transcription stream.

What happens to live audio transcription if the microphone device disconnects unexpectedly?

Live audio transcription handles microphone device loss and recovery gracefully through built-in resilience. The STT service is designed to ensure continuous operation by managing device errors and automatically recovering the audio processing pipeline.

What is the best way to integrate spoken commands into a Twitch chat display?

The best way to integrate spoken commands into a Twitch chat display is using a real-time STT pipeline that forwards transcribed text. This speech-to-text approach captures live audio and routes the processed text directly to your display or bot integration.

Does real-time speech-to-text processing require external dependencies to handle audio input?

No, real-time speech-to-text processing operates without external dependencies, handling audio recording, transcription initialization, and result forwarding internally. You only need to provide the audio input device to begin transcribing live speech.

Why does my speech-to-text service stop forwarding transcribed text during live audio processing?

Speech-to-text forwarding may stop due to microphone device loss or threshold misconfiguration during live audio processing. The STT service includes robust error handling to detect device loss and apply recovery protocols to resume transcription.