Voice call TTS and inbound calls

​

TTS for calls

{
  tts: {
    provider: "elevenlabs",
    providers: {
      elevenlabs: {
        speakerVoiceId: "pMsXgVXv3BLzUgSXRplE",
        modelId: "eleven_multilingual_v2",
      },
    },
  },
}

• Legacy tts.<provider> keys inside plugin config (openai, elevenlabs, microsoft, edge) are repaired by openclaw doctor --fix; committed config should use tts.providers.<provider>.
• Core TTS is used when Twilio media streaming is enabled; otherwise calls fall back to provider-native voices.
• If a Twilio media stream is already active, Voice Call does not fall back to TwiML <Say>. If telephony TTS is unavailable in that state, the playback request fails instead of mixing two playback paths.
• When telephony TTS falls back to a secondary provider, Voice Call logs a warning with the provider chain (from, to, attempts) for debugging.
• When Twilio barge-in or stream teardown clears the pending TTS queue, queued playback requests settle instead of hanging callers awaiting playback completion.
• Resumed caller speech discards older automatic replies that are still being generated. Twilio streaming reacts to speech-start and partial transcripts; carrier webhook calls react when a new speech event arrives. Explicit speech requests remain available, and already accepted agent work can finish without speaking an obsolete reply.

​

TTS examples

{
  tts: {
    provider: "openai",
    providers: {
      openai: { speakerVoice: "alloy" },
    },
  },
}

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          tts: {
            provider: "elevenlabs",
            providers: {
              elevenlabs: {
                apiKey: "elevenlabs_key",
                speakerVoiceId: "pMsXgVXv3BLzUgSXRplE",
                modelId: "eleven_multilingual_v2",
              },
            },
          },
        },
      },
    },
  },
}

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          tts: {
            providers: {
              openai: {
                model: "gpt-4o-mini-tts",
                speakerVoice: "marin",
              },
            },
          },
        },
      },
    },
  },
}

​

Inbound calls

{
  inboundPolicy: "allowlist",
  allowFrom: ["+15550001234"],
  inboundGreeting: "Hello! How can I help?",
}

​

Per-number routing

• inboundGreeting
• tts
• agentId
• responseModel
• responseSystemPrompt
• responseTimeoutMs

{
  inboundGreeting: "Hello from the main line.",
  responseSystemPrompt: "You are the default voice assistant.",
  tts: {
    provider: "openai",
    providers: {
      openai: { speakerVoice: "coral" },
    },
  },
  numbers: {
    "+15550001111": {
      inboundGreeting: "Silver Fox Cards, how can I help?",
      responseSystemPrompt: "You are a concise baseball card specialist.",
      tts: {
        providers: {
          openai: { speakerVoice: "alloy" },
        },
      },
    },
  },
}

​

Spoken output contract

• Ignores payloads marked as reasoning/error content.
• Parses direct JSON, fenced JSON, or inline "spoken" keys.
• Falls back to plain text and removes likely planning/meta lead-in paragraphs.

​

Conversation startup behavior

• Barge-in queue clear and auto-response are suppressed only while the initial greeting is actively speaking.
• If initial playback fails, the call returns to listening and the initial message remains queued for retry.
• Initial playback for Twilio streaming starts on stream connect without extra delay.
• Barge-in aborts active playback and clears queued-but-not-yet-playing Twilio TTS entries. Cleared entries resolve as skipped, so follow-up response logic can continue without waiting on audio that will never play.
• Realtime voice conversations use the realtime stream’s own opening turn. Voice Call does not post a legacy <Say> TwiML update for that initial message, so outbound <Connect><Stream> sessions stay attached.

​

Twilio stream disconnect grace

• If the stream reconnects during that window, auto-end is canceled.
• If no stream re-registers after the grace period, the call is ended to prevent stuck active calls.
• Realtime bridge/session resources, queued audio, transcript ownership, and in-flight consult work close immediately. Only call/provider finalization waits for reconnect.

​

Stale call reaper

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          maxDurationSeconds: 300,
          staleCallReaperSeconds: 120,
        },
      },
    },
  },
}