skills.rest
FutureAtoms
FutureAtomsCOMMUNITY
Explore all skills by this author →
GitHub

livekit-stt

Configure Speech-to-Text models for LiveKit agents with streaming and batch transcription.

1|Updated Mar 11, 2026
Search Tags:#transcription#voice ai#speech-to-text#deepgram#livekit#stt#assemblyai
One-click install
npx skills add https://github.com/FutureAtoms/claude-skills-backup --skill livekit-stt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: livekit-stt
Source: https://github.com/FutureAtoms/claude-skills-backup/tree/main/livekit-stt
Command: npx skills add https://github.com/FutureAtoms/claude-skills-backup --skill livekit-stt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies the configuration of Speech-to-Text (STT) models for LiveKit agents, enabling seamless voice-to-text transcription for AI applications.

Core Features & Use Cases

  • STT Model Configuration: Easily set up various STT providers like Deepgram, AssemblyAI, Whisper, and more.
  • Language Support: Configure for single or multiple languages, including auto-detection.
  • Streaming & Batch Processing: Supports both real-time streaming transcription and batch processing after speech ends.
  • Use Case: Integrate advanced STT capabilities into your LiveKit voice AI agent to accurately transcribe user speech in real-time, improving the agent's responsiveness and understanding.

Quick Start

Configure the LiveKit STT skill to use the Deepgram Nova-3 model for English.

Frequently Asked Questions about livekit-stt

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

FAQPage Schema
How do I configure speech-to-text for LiveKit agents?▼

To configure speech-to-text for LiveKit agents, you select an STT provider like Deepgram, AssemblyAI, or Whisper, and define settings for real-time streaming or batch transcription within the agent session.

Can I use Deepgram or AssemblyAI for real-time voice transcription?▼

Yes, you can use Deepgram or AssemblyAI for real-time voice transcription. The configuration supports streaming transcription to capture user speech continuously as it happens during a LiveKit agent session.

Does LiveKit STT support language auto-detection and keyword boosting?▼

LiveKit STT supports language auto-detection for single or multiple languages, alongside keyword boosting and endpointing, ensuring accurate transcription across diverse conversational contexts.

What is the difference between streaming and batch transcription in voice AI?▼

Streaming transcription processes audio in real-time during speech, while batch transcription processes the audio after speech ends, offering a trade-off between immediate responsiveness and complete processing accuracy.

How do I set up the Deepgram Nova-3 model for English transcription?▼

To set up the Deepgram Nova-3 model for English transcription, configure the LiveKit STT skill parameters to specify Deepgram as the provider and select English as the target language.

Related Skills

Explore More Software Engineering Skills→
FutureAtomsFutureAtoms
1

livekit-tts

Configure multi-provider TTS models for LiveKit agents with voice customization.

Community
Advanced
Nidhi786sharmaNidhi786sharma
3

Restaurant Bot

Handle restaurant menu inquiries, offers, and orders via Watson Assistant.

Community
Intermediate
EmeaAppGbbEmeaAppGbb

Azure AI Projects Client Library Skill

Guide Azure AI Projects Python SDK usage for building and deploying AI applications.

Official
Advanced
omarshahineomarshahine
155

speech-recognition

Transcribe live microphone input and audio files with Apple's Speech framework.

Community
Intermediate