Skip to main content
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.
PropertyValue
Provider idgradium
AuthGRADIUM_API_KEY or config apiKey
Base URLhttps://api.gradium.ai (default)
Default voiceEmma (YTpq7expH9539ERJ)

​
Install plugin

Gradium is an official external plugin. Install it, then restart Gateway: 
openclaw plugins install @openclaw/gradium-speech
openclaw 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_..."

​
Config

{
  messages: {
    tts: {
      auto: "always",
      provider: "gradium",
      providers: {
        gradium: {
          speakerVoiceId: "YTpq7expH9539ERJ",
          // apiKey: "${GRADIUM_API_KEY}",
          // baseUrl: "https://api.gradium.ai",
        },
      },
    },
  },
}
KeyTypeDescription
messages.tts.providers.gradium.apiKeystringResolved API key. Supports ${ENV} and secret refs.
messages.tts.providers.gradium.baseUrlstringAPI origin override. Trailing slashes stripped. Default https://api.gradium.ai.
messages.tts.providers.gradium.speakerVoiceIdstringDefault voice id used when no directive override is present.
Output format is chosen automatically by target surface (see Output) and is not configurable in openclaw.json.

​
Voices

NameVoice ID
Arthur3jUdJyOi9pgbxBTK
Christina2H4HY2CBNyJHBCrP
Emma (default)YTpq7expH9539ERJ
JohnKWJiFWu2O9nMPYcR
KentLFZvm12tW_z0xfGo
SydneyjtEKaLYNn6iif5PR
TiffanyEu9iL_CYe8N-Gkx_

​
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.
TargetFormatFile extSample rateVoice-compatible flag
Standard audiowav.wavproviderno
Voice noteopus.opusprovideryes
Telephonyulaw_8000n/a8 kHzn/a

​
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.