Gradium

Gradium is a text-to-speech provider for OpenClaw. It renders standard audio replies (WAV), voice-note-compatible Opus output, and 8 kHz u-law audio for telephony surfaces.

Install plugin

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

openclaw plugins install @openclaw/gradium-speechopenclaw gateway restart

Setup

Create a Gradium API key, then expose it with an env var or the config key. Config takes precedence over the env var.

export GRADIUM_API_KEY="gsk_..."

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

Config

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

Output format is chosen automatically by target surface (see Output) and is not configurable in openclaw.json.

Voices

Per-message voice override

When the active speech policy allows voice overrides, switch voices inline with a directive token (any of these are equivalent, all take 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 ignored.

Output

Output format is selected by target surface; the provider does not synthesize other formats.

Auto-select order

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

Related

• Text-to-Speech
• Media Overview