Gradium Text-to-Speech Provider Integration in OpenClaw

Gradium functions as a text-to-speech provider within OpenClaw. It can produce standard WAV audio replies, Opus output suitable for voice notes, and 8 kHz u-law audio intended for telephony interfaces.

Install plugin

Gradium ships as an official external plugin. After installing it, restart Gateway:

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

Setup

Obtain an API key from Gradium, then make it available either through an environment variable or a configuration key. When both are set, the configuration key takes priority.

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 determined automatically by the target surface (refer to Output) and cannot be adjusted within openclaw.json.

Voices

Per-message voice override

If the active speech policy permits voice overrides, you can switch voices inline using a directive token. All of the following are equivalent and accept a provider-native voice ID:

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

When the speech policy disallows voice overrides, the directive is still consumed but has no effect.

Output

The target surface dictates the output format; the provider does not generate any other formats.

Auto-select order

Among the configured TTS providers, Gradium's auto-select priority is 30. For details on how OpenClaw selects the active provider when tts.provider is not fixed, see Text-to-Speech.

Related

• Text-to-Speech
• Media Overview