Gradium Text-to-Speech Provider for OpenClaw

Gradium is a text-to-speech provider for OpenClaw. It can produce standard WAV audio replies, Opus output compatible with voice notes, and 8 kHz u-law audio for telephony systems.

Install plugin

Gradium ships as an official external plugin. Install it, then restart Gateway:

openclaw plugins install @openclaw/gradium-speech
openclaw gateway restart

Setup

Generate a Gradium API key and make it available through an environment variable or a config key. The config key overrides the environment variable.

Env var

export GRADIUM_API_KEY="gsk_..."

Config key

{
  tts: {
    auto: "always",
    provider: "gradium",
    providers: {
      gradium: {
        apiKey: "${GRADIUM_API_KEY}",
      },
    },
  },
}

Config

{
  tts: {
    auto: "always",
    provider: "gradium",
    providers: {
      gradium: {
        speakerVoiceId: "YTpq7expH9539ERJ",
        // apiKey: "${GRADIUM_API_KEY}",
        // baseUrl: "https://api.gradium.ai",
      },
    },
  },
}

The output format is selected automatically based on the target surface (see Output) and cannot be configured in openclaw.json.

Voices

Per-message voice override

When the active speech policy permits voice overrides, you can switch voices inline using a directive token (all of these are equivalent, and each accepts a provider-native voice id):

/voice:LFZvm12tW_z0xfGo
/voice_id:LFZvm12tW_z0xfGo
/voiceid:LFZvm12tW_z0xfGo
/gradium_voice:LFZvm12tW_z0xfGo
/gradiumvoice:LFZvm12tW_z0xfGo

If the speech policy disables voice overrides, the directive is consumed but silently ignored.

Output

The output format is chosen by the target surface; the provider does not generate other formats.

Auto-select order

Among the configured TTS providers, Gradium's auto-select order is 30. See Text-to-Speech for details on how OpenClaw selects the active provider when tts.provider is not pinned.

Related

• Text-to-Speech
• Media Overview