discord-voice

Route Discord voice speech through STT, Claude processing, and TTS playback.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/gevrey/openclaw_backup --skill discord-voice-gevrey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: discord-voice
Source: https://github.com/gevrey/openclaw_backup/tree/main/skills/discord-voice
Command: npx skills add https://github.com/gevrey/openclaw_backup --skill discord-voice-gevrey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and assets (resource) components.

What problem does it solve?

Real-time voice conversations in Discord channels are challenging to transcribe, route to an agent (Claude), and respond to in-channel dialogue, causing latency and context drops.

Core Features & Use Cases

  • Real-time speech-to-text and text-to-speech integration with Claude, OpenAI, ElevenLabs, Kokoro (local) and streaming options
  • Agent routing: transcriptions are sent to Claude and replies are spoken back in the voice channel
  • Robust fallbacks and VAD-based recording to improve reliability in noisy environments
  • Use cases include live support, team collaboration, and interactive meetings within Discord voice channels

Quick Start

Join a Discord voice channel and start speaking to trigger real-time transcription and response.

Frequently Asked Questions about discord-voice

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

FAQPage Schema
How do I get real-time transcription and AI voice responses in a Discord voice channel?

Real-time transcription and AI voice responses in Discord are enabled by routing speech through STT, processing via Claude, and speaking replies back using TTS with configurable streaming and fallback options.

Can I use Claude as a voice agent for live support and in-channel meetings in Discord?

Yes, Claude can act as a voice agent for live support and in-channel meetings by processing routed transcriptions and generating spoken replies directly in the Discord voice channel.

What providers can I use for speech-to-text and text-to-speech integration with a Discord voice bot?

You can configure STT and TTS providers including OpenAI, ElevenLabs, and Kokoro for local processing, alongside Claude for agent routing and response generation.

Do I need ffmpeg and OpenClaw integration to run real-time Discord voice AI?

Yes, you need ffmpeg as a system dependency and OpenClaw integration to route voice data, along with valid API keys for your chosen STT and TTS providers.

How does voice activity detection handle noisy environments during Discord voice transcription?

VAD-based recording improves transcription reliability in noisy environments by isolating active speech segments before routing them to the STT provider for processing.

Why does my Discord voice AI drop context or experience latency during live conversations?

Context drops and latency occur when real-time speech-to-text fails to stream continuously or agent routing lacks proper fallback mechanisms during live Discord channel conversations.