openclaw/docs/plugins/voice-call.md

summary, read_when, title, sidebarTitle

summary	read_when	title	sidebarTitle
Place outbound and accept inbound voice calls via Twilio, Telnyx, or Plivo, with optional realtime voice and streaming transcription	You want to place an outbound voice call from OpenClaw You are configuring or developing the voice-call plugin You need realtime voice or streaming transcription on telephony	Voice call plugin	Voice call

Voice calls for OpenClaw via a plugin. Supports outbound notifications, multi-turn conversations, full-duplex realtime voice, streaming transcription, and inbound calls with allowlist policies.

Current providers: twilio (Programmable Voice + Media Streams), telnyx (Call Control v2), plivo (Voice API + XML transfer + GetInput speech), mock (dev/no network).

The Voice Call plugin runs **inside the Gateway process**. If you use a remote Gateway, install and configure the plugin on the machine running the Gateway, then restart the Gateway to load it.

Quick start

```bash openclaw plugins install @openclaw/voice-call ``` ```bash PLUGIN_SRC=./path/to/local/voice-call-plugin openclaw plugins install "$PLUGIN_SRC" cd "$PLUGIN_SRC" && pnpm install ```

If npm reports the OpenClaw-owned package as deprecated, that package version
is from an older external package train; use a current packaged OpenClaw
build or the local folder path until a newer npm package is published.

Restart the Gateway afterwards so the plugin loads.

Set config under `plugins.entries.voice-call.config` (see [Configuration](#configuration) below for the full shape). At minimum: `provider`, provider credentials, `fromNumber`, and a publicly reachable webhook URL. ```bash openclaw voicecall setup ```

The default output is readable in chat logs and terminals. It checks
plugin enablement, provider credentials, webhook exposure, and that
only one audio mode (`streaming` or `realtime`) is active. Use
`--json` for scripts.

```bash openclaw voicecall smoke openclaw voicecall smoke --to "+15555550123" ```

Both are dry runs by default. Add `--yes` to actually place a short
outbound notify call:

```bash
openclaw voicecall smoke --to "+15555550123" --yes
```

For Twilio, Telnyx, and Plivo, setup must resolve to a **public webhook URL**. If `publicUrl`, the tunnel URL, the Tailscale URL, or the serve fallback resolves to loopback or private network space, setup fails instead of starting a provider that cannot receive carrier webhooks.

Configuration

If enabled: true but the selected provider is missing credentials, Gateway startup logs a setup-incomplete warning with the missing keys and skips starting the runtime. Commands, RPC calls, and agent tools still return the exact missing provider configuration when used.

Voice-call credentials accept SecretRefs. `plugins.entries.voice-call.config.twilio.authToken` and `plugins.entries.voice-call.config.tts.providers.*.apiKey` resolve through the standard SecretRef surface; see [SecretRef credential surface](/reference/secretref-credential-surface).

{
  plugins: {
    entries: {
      "voice-call": {
        enabled: true,
        config: {
          provider: "twilio", // or "telnyx" | "plivo" | "mock"
          fromNumber: "+15550001234", // or TWILIO_FROM_NUMBER for Twilio
          toNumber: "+15550005678",

          twilio: {
            accountSid: "ACxxxxxxxx",
            authToken: "...",
          },
          telnyx: {
            apiKey: "...",
            connectionId: "...",
            // Telnyx webhook public key from the Mission Control Portal
            // (Base64; can also be set via TELNYX_PUBLIC_KEY).
            publicKey: "...",
          },
          plivo: {
            authId: "MAxxxxxxxxxxxxxxxxxxxx",
            authToken: "...",
          },

          // Webhook server
          serve: {
            port: 3334,
            path: "/voice/webhook",
          },

          // Webhook security (recommended for tunnels/proxies)
          webhookSecurity: {
            allowedHosts: ["voice.example.com"],
            trustedProxyIPs: ["100.64.0.1"],
          },

          // Public exposure (pick one)
          // publicUrl: "https://example.ngrok.app/voice/webhook",
          // tunnel: { provider: "ngrok" },
          // tailscale: { mode: "funnel", path: "/voice/webhook" },

          outbound: {
            defaultMode: "notify", // notify | conversation
          },

          streaming: { enabled: true /* see Streaming transcription */ },
          realtime: { enabled: false /* see Realtime voice */ },
        },
      },
    },
  },
}

- Twilio, Telnyx, and Plivo all require a **publicly reachable** webhook URL. - `mock` is a local dev provider (no network calls). - Telnyx requires `telnyx.publicKey` (or `TELNYX_PUBLIC_KEY`) unless `skipSignatureVerification` is true. - `skipSignatureVerification` is for local testing only. - On ngrok free tier, set `publicUrl` to the exact ngrok URL; signature verification is always enforced. - `tunnel.allowNgrokFreeTierLoopbackBypass: true` allows Twilio webhooks with invalid signatures **only** when `tunnel.provider="ngrok"` and `serve.bind` is loopback (ngrok local agent). Local dev only. - Ngrok free-tier URLs can change or add interstitial behaviour; if `publicUrl` drifts, Twilio signatures fail. Production: prefer a stable domain or a Tailscale funnel. - `streaming.preStartTimeoutMs` closes sockets that never send a valid `start` frame. - `streaming.maxPendingConnections` caps total unauthenticated pre-start sockets. - `streaming.maxPendingConnectionsPerIp` caps unauthenticated pre-start sockets per source IP. - `streaming.maxConnections` caps total open media stream sockets (pending + active). Older configs using `provider: "log"`, `twilio.from`, or legacy `streaming.*` OpenAI keys are rewritten by `openclaw doctor --fix`. Runtime fallback still accepts the old voice-call keys for now, but the rewrite path is `openclaw doctor --fix` and the compat shim is temporary.

Auto-migrated streaming keys:

- `streaming.sttProvider` → `streaming.provider`
- `streaming.openaiApiKey` → `streaming.providers.openai.apiKey`
- `streaming.sttModel` → `streaming.providers.openai.model`
- `streaming.silenceDurationMs` → `streaming.providers.openai.silenceDurationMs`
- `streaming.vadThreshold` → `streaming.providers.openai.vadThreshold`

Realtime voice conversations

realtime selects a full-duplex realtime voice provider for live call audio. It is separate from streaming, which only forwards audio to realtime transcription providers.

`realtime.enabled` cannot be combined with `streaming.enabled`. Pick one audio mode per call.

Current runtime behaviour:

• realtime.enabled is supported for Twilio Media Streams.
• realtime.provider is optional. If unset, Voice Call uses the first registered realtime voice provider.
• Bundled realtime voice providers: Google Gemini Live (google) and OpenAI (openai), registered by their provider plugins.
• Provider-owned raw config lives under realtime.providers.<providerId>.
• Voice Call exposes the shared openclaw_agent_consult realtime tool by default. The realtime model can call it when the caller asks for deeper reasoning, current information, or normal OpenClaw tools.
• If realtime.provider points at an unregistered provider, or no realtime voice provider is registered at all, Voice Call logs a warning and skips realtime media instead of failing the whole plugin.
• Consult session keys reuse the existing voice session when available, then fall back to the caller/callee phone number so follow-up consult calls keep context during the call.

Tool policy

realtime.toolPolicy controls the consult run:

Policy	Behavior
safe-read-only	Expose the consult tool and limit the regular agent to read, web_search, web_fetch, x_search, memory_search, and memory_get.
owner	Expose the consult tool and let the regular agent use the normal agent tool policy.
none	Do not expose the consult tool. Custom realtime.tools are still passed through to the realtime provider.

Realtime provider examples

Defaults: API key from `realtime.providers.google.apiKey`, `GEMINI_API_KEY`, or `GOOGLE_GENERATIVE_AI_API_KEY`; model `gemini-2.5-flash-native-audio-preview-12-2025`; voice `Kore`.

```json5
{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          provider: "twilio",
          inboundPolicy: "allowlist",
          allowFrom: ["+15550005678"],
          realtime: {
            enabled: true,
            provider: "google",
            instructions: "Speak briefly. Call openclaw_agent_consult before using deeper tools.",
            toolPolicy: "safe-read-only",
            providers: {
              google: {
                apiKey: "${GEMINI_API_KEY}",
                model: "gemini-2.5-flash-native-audio-preview-12-2025",
                voice: "Kore",
              },
            },
          },
        },
      },
    },
  },
}
```

```json5 { plugins: { entries: { "voice-call": { config: { realtime: { enabled: true, provider: "openai", providers: { openai: { apiKey: "${OPENAI_API_KEY}" }, }, }, }, }, }, }, } ```

See Google provider and OpenAI provider for provider-specific realtime voice options.

Streaming transcription

streaming selects a realtime transcription provider for live call audio.

Current runtime behavior:

• streaming.provider is optional. If unset, Voice Call uses the first registered realtime transcription provider.
• Bundled realtime transcription providers: Deepgram (deepgram), ElevenLabs (elevenlabs), Mistral (mistral), OpenAI (openai), and xAI (xai), registered by their provider plugins.
• Provider-owned raw config lives under streaming.providers.<providerId>.
• After Twilio sends an accepted stream start message, Voice Call registers the stream immediately, queues inbound media through the transcription provider while the provider connects, and starts the initial greeting only after realtime transcription is ready.
• If streaming.provider points at an unregistered provider, or none is registered, Voice Call logs a warning and skips media streaming instead of failing the whole plugin.

Streaming provider examples

Defaults: API key `streaming.providers.openai.apiKey` or `OPENAI_API_KEY`; model `gpt-4o-transcribe`; `silenceDurationMs: 800`; `vadThreshold: 0.5`.

```json5
{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          streaming: {
            enabled: true,
            provider: "openai",
            streamPath: "/voice/stream",
            providers: {
              openai: {
                apiKey: "sk-...", // optional if OPENAI_API_KEY is set
                model: "gpt-4o-transcribe",
                silenceDurationMs: 800,
                vadThreshold: 0.5,
              },
            },
          },
        },
      },
    },
  },
}
```

Defaults: API key `streaming.providers.xai.apiKey` or `XAI_API_KEY`; endpoint `wss://api.x.ai/v1/stt`; encoding `mulaw`; sample rate `8000`; `endpointingMs: 800`; `interimResults: true`.

```json5
{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          streaming: {
            enabled: true,
            provider: "xai",
            streamPath: "/voice/stream",
            providers: {
              xai: {
                apiKey: "${XAI_API_KEY}", // optional if XAI_API_KEY is set
                endpointingMs: 800,
                language: "en",
              },
            },
          },
        },
      },
    },
  },
}
```

TTS for calls

Voice Call uses the core messages.tts configuration for streaming speech on calls. You can override it under the plugin config with the same shape — it deep-merges with messages.tts.

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

**Microsoft speech is ignored for voice calls.** Telephony audio needs PCM; the current Microsoft transport does not expose telephony PCM output.

Behavior notes:

• 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.

TTS examples

```json5 { messages: { tts: { provider: "openai", providers: { openai: { voice: "alloy" }, }, }, }, } ``` ```json5 { plugins: { entries: { "voice-call": { config: { tts: { provider: "elevenlabs", providers: { elevenlabs: { apiKey: "elevenlabs_key", voiceId: "pMsXgVXv3BLzUgSXRplE", modelId: "eleven_multilingual_v2", }, }, }, }, }, }, }, } ``` ```json5 { plugins: { entries: { "voice-call": { config: { tts: { providers: { openai: { model: "gpt-4o-mini-tts", voice: "marin", }, }, }, }, }, }, }, } ```

Inbound calls

Inbound policy defaults to disabled. To enable inbound calls, set:

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

`inboundPolicy: "allowlist"` is a low-assurance caller-ID screen. The plugin normalizes the provider-supplied `From` value and compares it to `allowFrom`. Webhook verification authenticates provider delivery and payload integrity, but it does **not** prove PSTN/VoIP caller-number ownership. Treat `allowFrom` as caller-ID filtering, not strong caller identity.

Auto-responses use the agent system. Tune with responseModel, responseSystemPrompt, and responseTimeoutMs.

Spoken output contract

For auto-responses, Voice Call appends a strict spoken-output contract to the system prompt:

{"spoken":"..."}

Voice Call extracts speech text defensively:

• 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.

This keeps spoken playback focused on caller-facing text and avoids leaking planning text into audio.

Conversation startup behavior

For outbound conversation calls, first-message handling is tied to live playback state:

• 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

When a Twilio media stream disconnects, Voice Call waits 2000 ms before auto-ending the call:

• 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.

Stale call reaper

Use staleCallReaperSeconds to end calls that never receive a terminal webhook (for example, notify-mode calls that never complete). The default is 0 (disabled).

Recommended ranges:

• Production: 120–300 seconds for notify-style flows.
• Keep this value higher than maxDurationSeconds so normal calls can finish. A good starting point is maxDurationSeconds + 30–60 seconds.

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          maxDurationSeconds: 300,
          staleCallReaperSeconds: 360,
        },
      },
    },
  },
}

Webhook security

When a proxy or tunnel sits in front of the Gateway, the plugin reconstructs the public URL for signature verification. These options control which forwarded headers are trusted:

Allowlist hosts from forwarding headers. Trust forwarded headers without an allowlist. Only trust forwarded headers when the request remote IP matches the list.

Additional protections:

• Webhook replay protection is enabled for Twilio and Plivo. Replayed valid webhook requests are acknowledged but skipped for side effects.
• Twilio conversation turns include a per-turn token in <Gather> callbacks, so stale/replayed speech callbacks cannot satisfy a newer pending transcript turn.
• Unauthenticated webhook requests are rejected before body reads when the provider's required signature headers are missing.
• The voice-call webhook uses the shared pre-auth body profile (64 KB / 5 seconds) plus a per-IP in-flight cap before signature verification.

Example with a stable public host:

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          publicUrl: "https://voice.example.com/voice/webhook",
          webhookSecurity: {
            allowedHosts: ["voice.example.com"],
          },
        },
      },
    },
  },
}

CLI

openclaw voicecall call --to "+15555550123" --message "Hello from OpenClaw"
openclaw voicecall start --to "+15555550123"   # alias for call
openclaw voicecall continue --call-id <id> --message "Any questions?"
openclaw voicecall speak --call-id <id> --message "One moment"
openclaw voicecall dtmf --call-id <id> --digits "ww123456#"
openclaw voicecall end --call-id <id>
openclaw voicecall status --call-id <id>
openclaw voicecall tail
openclaw voicecall latency                      # summarize turn latency from logs
openclaw voicecall expose --mode funnel

latency reads calls.jsonl from the default voice-call storage path. Use --file <path> to point at a different log and --last <n> to limit analysis to the last N records (default 200). Output includes p50/p90/p99 for turn latency and listen-wait times.

Agent tool

Tool name: voice_call.

Action	Args
initiate_call	message, to?, mode?
continue_call	callId, message
speak_to_user	callId, message
send_dtmf	callId, digits
end_call	callId
get_status	callId

This repo ships a matching skill doc at skills/voice-call/SKILL.md.

Gateway RPC

Method	Args
voicecall.initiate	to?, message, mode?
voicecall.continue	callId, message
voicecall.speak	callId, message
voicecall.dtmf	callId, digits
voicecall.end	callId
voicecall.status	callId

Related

• Talk mode
• Text-to-speech
• Voice wake