ElevenLabs：模型入口要怎么敲门

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：OpenClaw uses ElevenLabs for text-to-speech, batch speech-to-text with Scribe v2, and 一边说一边送ing STT with Scribe v2 Real…。

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

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Set ELEVENLABS_对话接口_KEY in the environment. XI_对话接口_KEY is also accepted for compatibility with existing ElevenLabs 工具小…。

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

export ELEVENLABS_API_KEY="..."

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Set 聪明脑袋模型Id to eleven_v3 to use ElevenLabs v3 TTS. OpenClaw keeps eleven_multilingual_v2 as the default for existing i…。

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

Set modelId to eleven_v3 to use ElevenLabs v3 TTS. OpenClaw keeps eleven_multilingual_v2 as the default for existing installs.

Discord voice channels use ElevenLabs' streaming TTS endpoint when ElevenLabs is the selected voice.tts/messages.tts provider. Playback starts from the returned audio stream instead of waiting for OpenClaw to download and write the whole audio file first. latencyTier maps to ElevenLabs' optimize_streaming_latency query parameter for models that accept it; OpenClaw omits that parameter for eleven_v3, which rejects it.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Use Scribe v2 for inbound audio attachments and short recorded voice segments: OpenClaw sends multipart audio to Eleven…。

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

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

OpenClaw sends multipart audio to ElevenLabs /v1/speech-to-text with model_id: "scribe_v2". Language hints map to language_code when present.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：The bundled elevenlabs 新本领插件 registers Scribe v2 Realtime for Voice Call and Google Meet 机器人朋友-mode 一边说一边送ing transcrip…。

The bundled elevenlabs plugin registers Scribe v2 Realtime for Voice Call and Google Meet agent-mode streaming transcription.

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

Note

Voice Call receives Twilio media as 8 kHz G.711 u-law. The ElevenLabs realtime provider defaults to ulaw_8000, so telephony frames can be forwarded without transcoding.

For Google Meet agent mode, set plugins.entries.google-meet.config.realtime.transcriptionProvider to "elevenlabs" and configure the same provider block under plugins.entries.google-meet.config.realtime.providers.elevenlabs.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：---。

• Text-to-speech
• Google Meet
• Model selection

---