ElevenLabs

OpenClaw uses ElevenLabs for text-to-speech, batch speech-to-text with Scribe v2, and Voice Call streaming STT with Scribe v2 Realtime.

Authentication

Set

in the environment. is also accepted for compatibility with existing ElevenLabs tooling.

bash
Copy
export ELEVENLABS_API_KEY="..."

Text-to-speech

json5
Copy
{
  messages: {
    tts: {
      providers: {
        elevenlabs: {
          apiKey: "${ELEVENLABS_API_KEY}",
          voiceId: "pMsXgVXv3BLzUgSXRplE",
          modelId: "eleven_multilingual_v2",
        },
      },
    },
  },
}

Set

to to use ElevenLabs v3 TTS. OpenClaw keeps as the default for existing installs.

Speech-to-text

Use Scribe v2 for inbound audio attachments and short recorded voice segments:

json5
Copy
{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "elevenlabs", model: "scribe_v2" }],
      },
    },
  },
}

OpenClaw sends multipart audio to ElevenLabs

with . Language hints map to when present.

Voice Call streaming STT

The bundled

plugin registers Scribe v2 Realtime for Voice Call streaming transcription.

json5
Copy
{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          streaming: {
            enabled: true,
            provider: "elevenlabs",
            providers: {
              elevenlabs: {
                apiKey: "${ELEVENLABS_API_KEY}",
                audioFormat: "ulaw_8000",
                commitStrategy: "vad",
                languageCode: "en",
              },
            },
          },
        },
      },
    },
  },
}

Related

• Text-to-speech
• Model selection