Skip to main content
Realtime voice enables spoken conversations with the AI. Audio is captured, transcribed, processed, and synthesized back to speech in real time.

​
Requirements

  • A realtime voice provider plugin (e.g. @wednesdayai/voice-openai)
  • A channel with voice support (currently: Discord voice channels)

​
Quick start

1

Install a voice provider plugin

openclaw plugins install @wednesdayai/voice-openai
2

Configure the provider

plugins:
  voice-openai:
    apiKey: ""   # or OPENAI_API_KEY
    model: "gpt-4o-realtime-preview"
    voice: "alloy"
3

Enable voice on a channel

channels:
  discord:
    voice:
      enabled: true
      provider: "voice-openai"
4

Restart the gateway

openclaw restart

​
Configuration reference

channels:
  discord:
    voice:
      enabled: false
      provider: ""
      vad:
        sensitivity: 0.5    # 0–1; higher = less noise-sensitive
        silenceMs: 800      # ms of silence to end a turn
      maxSessionMinutes: 60
      requirePermission: false
KeyTypeDefaultDescription
enabledbooleanfalseEnable voice for this channel
providerstring—Voice provider plugin name
vad.sensitivitynumber0.5Voice activity detection sensitivity (0–1)
vad.silenceMsinteger800Silence duration to end a turn
maxSessionMinutesinteger60Auto-end sessions after this duration (0 = no limit)
requirePermissionbooleanfalseRestrict to users with the voice permission

​
Troubleshooting

Run openclaw doctor --check voice to diagnose configuration issues.