Skip to main content
OpenClaw is a self-hosted agent gateway for messaging channels, agent sessions, and tool-driven workflows. Its bundled Gradium speech provider lets OpenClaw agents turn replies into audio, voice-note-compatible Opus output, or 8 kHz u-law audio for telephony surfaces.

OpenClaw Gradium provider

OpenClaw’s provider reference for Gradium TTS.

GitHub integration

View the OpenClaw Gradium extension source.

Gradium TTS guide

Gradium WebSocket TTS setup and streaming behavior.

Setup

Create a Gradium API key, then expose it to OpenClaw with an environment variable:
OpenClaw can also read the key from messages.tts.providers.gradium.apiKey in ~/.openclaw/openclaw.json.

Basic config

Set gradium as the TTS provider and choose a Gradium voice ID.
Use auto: "always" when every eligible agent reply should include audio. Use OpenClaw’s session commands or per-agent config when you need more targeted behavior.

Provider settings

Voices

OpenClaw’s Gradium provider defaults to Emma.

Output behavior

OpenClaw chooses the Gradium output format from the destination surface:

When to use OpenClaw with Gradium

  • Messaging-channel agents: speak replies across OpenClaw-supported channels without building per-channel audio delivery.
  • Voice-note workflows: send spoken responses as voice-compatible channel media.
  • Telephony surfaces: synthesize 8 kHz u-law audio for phone-oriented integrations.
  • Self-hosted agent stacks: keep OpenClaw’s local gateway model while using Gradium for speech output.