@openclaw/voice-call 2026.1.29

package/CHANGELOG.md

@@ -0,0 +1,78 @@
+# Changelog
+
+## 2026.1.29
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.26
+
+### Changes
+- Breaking: voice-call TTS now uses core `messages.tts` (plugin TTS config deep‑merges with core).
+- Telephony TTS supports OpenAI + ElevenLabs; Edge TTS is ignored for calls.
+- Removed legacy `tts.model`/`tts.voice`/`tts.instructions` plugin fields.
+- Ngrok free-tier bypass renamed to `tunnel.allowNgrokFreeTierLoopbackBypass` and gated to loopback + `tunnel.provider="ngrok"`.
+
+## 2026.1.23
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.22
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.21
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.20
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.17-1
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.17
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.16
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.15
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 2026.1.14
+
+### Changes
+- Version alignment with core OpenClaw release numbers.
+
+## 0.1.0
+
+### Highlights
+- First public release of the @openclaw/voice-call plugin.
+
+### Features
+- Providers: Twilio (Programmable Voice + Media Streams), Telnyx (Call Control v2), and mock provider for local dev.
+- Call flows: outbound notify vs. conversation modes, configurable auto‑hangup, and multi‑turn continuation.
+- Inbound handling: policy controls (disabled/allowlist/open), allowlist matching, and inbound greeting.
+- Webhooks: built‑in server with configurable bind/port/path plus `publicUrl` override.
+- Exposure helpers: ngrok + Tailscale serve/funnel; dev‑only signature bypass for ngrok free tier.
+- Streaming: OpenAI Realtime STT over media WebSocket with partial + final transcripts.
+- Speech: OpenAI TTS (model/voice/instructions) with Twilio `<Say>` fallback.
+- Tooling: `voice_call` tool actions for initiate/continue/speak/end/status.
+- Gateway RPC: `voicecall.initiate|continue|speak|end|status` (+ legacy `voicecall.start`).
+- CLI: `openclaw voicecall` commands (call/start/continue/speak/end/status/tail/expose).
+- Observability: JSONL call logs and `voicecall tail` for live inspection.
+- Response controls: `responseModel`, `responseSystemPrompt`, and `responseTimeoutMs` for auto‑responses.

package/README.md

@@ -0,0 +1,135 @@
+# @openclaw/voice-call
+
+Official Voice Call plugin for **OpenClaw**.
+
+Providers:
+- **Twilio** (Programmable Voice + Media Streams)
+- **Telnyx** (Call Control v2)
+- **Plivo** (Voice API + XML transfer + GetInput speech)
+- **Mock** (dev/no network)
+
+Docs: `https://docs.openclaw.ai/plugins/voice-call`
+Plugin system: `https://docs.openclaw.ai/plugin`
+
+## Install (local dev)
+
+### Option A: install via OpenClaw (recommended)
+
+```bash
+openclaw plugins install @openclaw/voice-call
+```
+
+Restart the Gateway afterwards.
+
+### Option B: copy into your global extensions folder (dev)
+
+```bash
+mkdir -p ~/.openclaw/extensions
+cp -R extensions/voice-call ~/.openclaw/extensions/voice-call
+cd ~/.openclaw/extensions/voice-call && pnpm install
+```
+
+## Config
+
+Put under `plugins.entries.voice-call.config`:
+
+```json5
+{
+  provider: "twilio", // or "telnyx" | "plivo" | "mock"
+  fromNumber: "+15550001234",
+  toNumber: "+15550005678",
+
+  twilio: {
+    accountSid: "ACxxxxxxxx",
+    authToken: "your_token"
+  },
+
+  plivo: {
+    authId: "MAxxxxxxxxxxxxxxxxxxxx",
+    authToken: "your_token"
+  },
+
+  // Webhook server
+  serve: {
+    port: 3334,
+    path: "/voice/webhook"
+  },
+
+  // Public exposure (pick one):
+  // publicUrl: "https://example.ngrok.app/voice/webhook",
+  // tunnel: { provider: "ngrok" },
+  // tailscale: { mode: "funnel", path: "/voice/webhook" }
+
+  outbound: {
+    defaultMode: "notify" // or "conversation"
+  },
+
+  streaming: {
+    enabled: true,
+    streamPath: "/voice/stream"
+  }
+}
+```
+
+Notes:
+- Twilio/Telnyx/Plivo require a **publicly reachable** webhook URL.
+- `mock` is a local dev provider (no network calls).
+- `tunnel.allowNgrokFreeTierLoopbackBypass: true` allows Twilio webhooks with invalid signatures **only** when `tunnel.provider="ngrok"` and `serve.bind` is loopback (ngrok local agent). Use for local dev only.
+
+## TTS for calls
+
+Voice Call uses the core `messages.tts` configuration (OpenAI or ElevenLabs) for
+streaming speech on calls. You can override it under the plugin config with the
+same shape — overrides deep-merge with `messages.tts`.
+
+```json5
+{
+  tts: {
+    provider: "openai",
+    openai: {
+      voice: "alloy"
+    }
+  }
+}
+```
+
+Notes:
+- Edge TTS is ignored for voice calls (telephony audio needs PCM; Edge output is unreliable).
+- Core TTS is used when Twilio media streaming is enabled; otherwise calls fall back to provider native voices.
+
+## CLI
+
+```bash
+openclaw voicecall call --to "+15555550123" --message "Hello from OpenClaw"
+openclaw voicecall continue --call-id <id> --message "Any questions?"
+openclaw voicecall speak --call-id <id> --message "One moment"
+openclaw voicecall end --call-id <id>
+openclaw voicecall status --call-id <id>
+openclaw voicecall tail
+openclaw voicecall expose --mode funnel
+```
+
+## Tool
+
+Tool name: `voice_call`
+
+Actions:
+- `initiate_call` (message, to?, mode?)
+- `continue_call` (callId, message)
+- `speak_to_user` (callId, message)
+- `end_call` (callId)
+- `get_status` (callId)
+
+## Gateway RPC
+
+- `voicecall.initiate` (to?, message, mode?)
+- `voicecall.continue` (callId, message)
+- `voicecall.speak` (callId, message)
+- `voicecall.end` (callId)
+- `voicecall.status` (callId)
+
+## Notes
+
+- Uses webhook signature verification for Twilio/Telnyx/Plivo.
+- `responseModel` / `responseSystemPrompt` control AI auto-responses.
+- Media streaming requires `ws` and OpenAI Realtime API key.

package/index.ts

@@ -0,0 +1,497 @@
+import { Type } from "@sinclair/typebox";
+import type { CoreConfig } from "./src/core-bridge.js";
+import {
+  VoiceCallConfigSchema,
+  resolveVoiceCallConfig,
+  validateProviderConfig,
+  type VoiceCallConfig,
+} from "./src/config.js";
+import { registerVoiceCallCli } from "./src/cli.js";
+import { createVoiceCallRuntime, type VoiceCallRuntime } from "./src/runtime.js";
+
+const voiceCallConfigSchema = {
+  parse(value: unknown): VoiceCallConfig {
+    const raw =
+      value && typeof value === "object" && !Array.isArray(value)
+        ? (value as Record<string, unknown>)
+        : {};
+
+    const twilio = raw.twilio as Record<string, unknown> | undefined;
+    const legacyFrom = typeof twilio?.from === "string" ? twilio.from : undefined;
+
+    const enabled = typeof raw.enabled === "boolean" ? raw.enabled : true;
+    const providerRaw = raw.provider === "log" ? "mock" : raw.provider;
+    const provider = providerRaw ?? (enabled ? "mock" : undefined);
+
+    return VoiceCallConfigSchema.parse({
+      ...raw,
+      enabled,
+      provider,
+      fromNumber: raw.fromNumber ?? legacyFrom,
+    });
+  },
+  uiHints: {
+    provider: {
+      label: "Provider",
+      help: "Use twilio, telnyx, or mock for dev/no-network.",
+    },
+    fromNumber: { label: "From Number", placeholder: "+15550001234" },
+    toNumber: { label: "Default To Number", placeholder: "+15550001234" },
+    inboundPolicy: { label: "Inbound Policy" },
+    allowFrom: { label: "Inbound Allowlist" },
+    inboundGreeting: { label: "Inbound Greeting", advanced: true },
+    "telnyx.apiKey": { label: "Telnyx API Key", sensitive: true },
+    "telnyx.connectionId": { label: "Telnyx Connection ID" },
+    "telnyx.publicKey": { label: "Telnyx Public Key", sensitive: true },
+    "twilio.accountSid": { label: "Twilio Account SID" },
+    "twilio.authToken": { label: "Twilio Auth Token", sensitive: true },
+    "outbound.defaultMode": { label: "Default Call Mode" },
+    "outbound.notifyHangupDelaySec": {
+      label: "Notify Hangup Delay (sec)",
+      advanced: true,
+    },
+    "serve.port": { label: "Webhook Port" },
+    "serve.bind": { label: "Webhook Bind" },
+    "serve.path": { label: "Webhook Path" },
+    "tailscale.mode": { label: "Tailscale Mode", advanced: true },
+    "tailscale.path": { label: "Tailscale Path", advanced: true },
+    "tunnel.provider": { label: "Tunnel Provider", advanced: true },
+    "tunnel.ngrokAuthToken": {
+      label: "ngrok Auth Token",
+      sensitive: true,
+      advanced: true,
+    },
+    "tunnel.ngrokDomain": { label: "ngrok Domain", advanced: true },
+    "tunnel.allowNgrokFreeTierLoopbackBypass": {
+      label: "Allow ngrok Free Tier (Loopback Bypass)",
+      advanced: true,
+    },
+    "streaming.enabled": { label: "Enable Streaming", advanced: true },
+    "streaming.openaiApiKey": {
+      label: "OpenAI Realtime API Key",
+      sensitive: true,
+      advanced: true,
+    },
+    "streaming.sttModel": { label: "Realtime STT Model", advanced: true },
+    "streaming.streamPath": { label: "Media Stream Path", advanced: true },
+    "tts.provider": {
+      label: "TTS Provider Override",
+      help: "Deep-merges with messages.tts (Edge is ignored for calls).",
+      advanced: true,
+    },
+    "tts.openai.model": { label: "OpenAI TTS Model", advanced: true },
+    "tts.openai.voice": { label: "OpenAI TTS Voice", advanced: true },
+    "tts.openai.apiKey": {
+      label: "OpenAI API Key",
+      sensitive: true,
+      advanced: true,
+    },
+    "tts.elevenlabs.modelId": { label: "ElevenLabs Model ID", advanced: true },
+    "tts.elevenlabs.voiceId": { label: "ElevenLabs Voice ID", advanced: true },
+    "tts.elevenlabs.apiKey": {
+      label: "ElevenLabs API Key",
+      sensitive: true,
+      advanced: true,
+    },
+    "tts.elevenlabs.baseUrl": { label: "ElevenLabs Base URL", advanced: true },
+    publicUrl: { label: "Public Webhook URL", advanced: true },
+    skipSignatureVerification: {
+      label: "Skip Signature Verification",
+      advanced: true,
+    },
+    store: { label: "Call Log Store Path", advanced: true },
+    responseModel: { label: "Response Model", advanced: true },
+    responseSystemPrompt: { label: "Response System Prompt", advanced: true },
+    responseTimeoutMs: { label: "Response Timeout (ms)", advanced: true },
+  },
+};
+
+const VoiceCallToolSchema = Type.Union([
+  Type.Object({
+    action: Type.Literal("initiate_call"),
+    to: Type.Optional(Type.String({ description: "Call target" })),
+    message: Type.String({ description: "Intro message" }),
+    mode: Type.Optional(Type.Union([Type.Literal("notify"), Type.Literal("conversation")])),
+  }),
+  Type.Object({
+    action: Type.Literal("continue_call"),
+    callId: Type.String({ description: "Call ID" }),
+    message: Type.String({ description: "Follow-up message" }),
+  }),
+  Type.Object({
+    action: Type.Literal("speak_to_user"),
+    callId: Type.String({ description: "Call ID" }),
+    message: Type.String({ description: "Message to speak" }),
+  }),
+  Type.Object({
+    action: Type.Literal("end_call"),
+    callId: Type.String({ description: "Call ID" }),
+  }),
+  Type.Object({
+    action: Type.Literal("get_status"),
+    callId: Type.String({ description: "Call ID" }),
+  }),
+  Type.Object({
+    mode: Type.Optional(Type.Union([Type.Literal("call"), Type.Literal("status")])),
+    to: Type.Optional(Type.String({ description: "Call target" })),
+    sid: Type.Optional(Type.String({ description: "Call SID" })),
+    message: Type.Optional(Type.String({ description: "Optional intro message" })),
+  }),
+]);
+
+const voiceCallPlugin = {
+  id: "voice-call",
+  name: "Voice Call",
+  description: "Voice-call plugin with Telnyx/Twilio/Plivo providers",
+  configSchema: voiceCallConfigSchema,
+  register(api) {
+    const config = resolveVoiceCallConfig(
+      voiceCallConfigSchema.parse(api.pluginConfig),
+    );
+    const validation = validateProviderConfig(config);
+
+    if (api.pluginConfig && typeof api.pluginConfig === "object") {
+      const raw = api.pluginConfig as Record<string, unknown>;
+      const twilio = raw.twilio as Record<string, unknown> | undefined;
+      if (raw.provider === "log") {
+        api.logger.warn(
+          "[voice-call] provider \"log\" is deprecated; use \"mock\" instead",
+        );
+      }
+      if (typeof twilio?.from === "string") {
+        api.logger.warn(
+          "[voice-call] twilio.from is deprecated; use fromNumber instead",
+        );
+      }
+    }
+
+    let runtimePromise: Promise<VoiceCallRuntime> | null = null;
+    let runtime: VoiceCallRuntime | null = null;
+
+    const ensureRuntime = async () => {
+      if (!config.enabled) {
+        throw new Error("Voice call disabled in plugin config");
+      }
+      if (!validation.valid) {
+        throw new Error(validation.errors.join("; "));
+      }
+      if (runtime) return runtime;
+      if (!runtimePromise) {
+        runtimePromise = createVoiceCallRuntime({
+          config,
+          coreConfig: api.config as CoreConfig,
+          ttsRuntime: api.runtime.tts,
+          logger: api.logger,
+        });
+      }
+      runtime = await runtimePromise;
+      return runtime;
+    };
+
+    const sendError = (respond: (ok: boolean, payload?: unknown) => void, err: unknown) => {
+      respond(false, { error: err instanceof Error ? err.message : String(err) });
+    };
+
+    api.registerGatewayMethod("voicecall.initiate", async ({ params, respond }) => {
+      try {
+        const message =
+          typeof params?.message === "string" ? params.message.trim() : "";
+        if (!message) {
+          respond(false, { error: "message required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const to =
+          typeof params?.to === "string" && params.to.trim()
+            ? params.to.trim()
+            : rt.config.toNumber;
+        if (!to) {
+          respond(false, { error: "to required" });
+          return;
+        }
+        const mode =
+          params?.mode === "notify" || params?.mode === "conversation"
+            ? params.mode
+            : undefined;
+        const result = await rt.manager.initiateCall(to, undefined, {
+          message,
+          mode,
+        });
+        if (!result.success) {
+          respond(false, { error: result.error || "initiate failed" });
+          return;
+        }
+        respond(true, { callId: result.callId, initiated: true });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerGatewayMethod("voicecall.continue", async ({ params, respond }) => {
+      try {
+        const callId =
+          typeof params?.callId === "string" ? params.callId.trim() : "";
+        const message =
+          typeof params?.message === "string" ? params.message.trim() : "";
+        if (!callId || !message) {
+          respond(false, { error: "callId and message required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const result = await rt.manager.continueCall(callId, message);
+        if (!result.success) {
+          respond(false, { error: result.error || "continue failed" });
+          return;
+        }
+        respond(true, { success: true, transcript: result.transcript });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerGatewayMethod("voicecall.speak", async ({ params, respond }) => {
+      try {
+        const callId =
+          typeof params?.callId === "string" ? params.callId.trim() : "";
+        const message =
+          typeof params?.message === "string" ? params.message.trim() : "";
+        if (!callId || !message) {
+          respond(false, { error: "callId and message required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const result = await rt.manager.speak(callId, message);
+        if (!result.success) {
+          respond(false, { error: result.error || "speak failed" });
+          return;
+        }
+        respond(true, { success: true });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerGatewayMethod("voicecall.end", async ({ params, respond }) => {
+      try {
+        const callId =
+          typeof params?.callId === "string" ? params.callId.trim() : "";
+        if (!callId) {
+          respond(false, { error: "callId required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const result = await rt.manager.endCall(callId);
+        if (!result.success) {
+          respond(false, { error: result.error || "end failed" });
+          return;
+        }
+        respond(true, { success: true });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerGatewayMethod("voicecall.status", async ({ params, respond }) => {
+      try {
+        const raw =
+          typeof params?.callId === "string"
+            ? params.callId.trim()
+            : typeof params?.sid === "string"
+              ? params.sid.trim()
+              : "";
+        if (!raw) {
+          respond(false, { error: "callId required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const call =
+          rt.manager.getCall(raw) || rt.manager.getCallByProviderCallId(raw);
+        if (!call) {
+          respond(true, { found: false });
+          return;
+        }
+        respond(true, { found: true, call });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerGatewayMethod("voicecall.start", async ({ params, respond }) => {
+      try {
+        const to = typeof params?.to === "string" ? params.to.trim() : "";
+        const message =
+          typeof params?.message === "string" ? params.message.trim() : "";
+        if (!to) {
+          respond(false, { error: "to required" });
+          return;
+        }
+        const rt = await ensureRuntime();
+        const result = await rt.manager.initiateCall(to, undefined, {
+          message: message || undefined,
+        });
+        if (!result.success) {
+          respond(false, { error: result.error || "initiate failed" });
+          return;
+        }
+        respond(true, { callId: result.callId, initiated: true });
+      } catch (err) {
+        sendError(respond, err);
+      }
+    });
+
+    api.registerTool({
+      name: "voice_call",
+      label: "Voice Call",
+      description:
+        "Make phone calls and have voice conversations via the voice-call plugin.",
+      parameters: VoiceCallToolSchema,
+      async execute(_toolCallId, params) {
+        const json = (payload: unknown) => ({
+          content: [
+            { type: "text", text: JSON.stringify(payload, null, 2) },
+          ],
+          details: payload,
+        });
+
+        try {
+          const rt = await ensureRuntime();
+
+          if (typeof params?.action === "string") {
+            switch (params.action) {
+              case "initiate_call": {
+                const message = String(params.message || "").trim();
+                if (!message) throw new Error("message required");
+                const to =
+                  typeof params.to === "string" && params.to.trim()
+                    ? params.to.trim()
+                    : rt.config.toNumber;
+                if (!to) throw new Error("to required");
+                const result = await rt.manager.initiateCall(to, undefined, {
+                  message,
+                  mode:
+                    params.mode === "notify" || params.mode === "conversation"
+                      ? params.mode
+                      : undefined,
+                });
+                if (!result.success) {
+                  throw new Error(result.error || "initiate failed");
+                }
+                return json({ callId: result.callId, initiated: true });
+              }
+              case "continue_call": {
+                const callId = String(params.callId || "").trim();
+                const message = String(params.message || "").trim();
+                if (!callId || !message) {
+                  throw new Error("callId and message required");
+                }
+                const result = await rt.manager.continueCall(callId, message);
+                if (!result.success) {
+                  throw new Error(result.error || "continue failed");
+                }
+                return json({ success: true, transcript: result.transcript });
+              }
+              case "speak_to_user": {
+                const callId = String(params.callId || "").trim();
+                const message = String(params.message || "").trim();
+                if (!callId || !message) {
+                  throw new Error("callId and message required");
+                }
+                const result = await rt.manager.speak(callId, message);
+                if (!result.success) {
+                  throw new Error(result.error || "speak failed");
+                }
+                return json({ success: true });
+              }
+              case "end_call": {
+                const callId = String(params.callId || "").trim();
+                if (!callId) throw new Error("callId required");
+                const result = await rt.manager.endCall(callId);
+                if (!result.success) {
+                  throw new Error(result.error || "end failed");
+                }
+                return json({ success: true });
+              }
+              case "get_status": {
+                const callId = String(params.callId || "").trim();
+                if (!callId) throw new Error("callId required");
+                const call =
+                  rt.manager.getCall(callId) ||
+                  rt.manager.getCallByProviderCallId(callId);
+                return json(call ? { found: true, call } : { found: false });
+              }
+            }
+          }
+
+          const mode = params?.mode ?? "call";
+          if (mode === "status") {
+            const sid =
+              typeof params.sid === "string" ? params.sid.trim() : "";
+            if (!sid) throw new Error("sid required for status");
+            const call =
+              rt.manager.getCall(sid) || rt.manager.getCallByProviderCallId(sid);
+            return json(call ? { found: true, call } : { found: false });
+          }
+
+          const to =
+            typeof params.to === "string" && params.to.trim()
+              ? params.to.trim()
+              : rt.config.toNumber;
+          if (!to) throw new Error("to required for call");
+          const result = await rt.manager.initiateCall(to, undefined, {
+            message:
+              typeof params.message === "string" && params.message.trim()
+                ? params.message.trim()
+                : undefined,
+          });
+          if (!result.success) {
+            throw new Error(result.error || "initiate failed");
+          }
+          return json({ callId: result.callId, initiated: true });
+        } catch (err) {
+          return json({
+            error: err instanceof Error ? err.message : String(err),
+          });
+        }
+      },
+    });
+
+    api.registerCli(
+      ({ program }) =>
+        registerVoiceCallCli({
+          program,
+          config,
+          ensureRuntime,
+          logger: api.logger,
+        }),
+      { commands: ["voicecall"] },
+    );
+
+    api.registerService({
+      id: "voicecall",
+      start: async () => {
+        if (!config.enabled) return;
+        try {
+          await ensureRuntime();
+        } catch (err) {
+          api.logger.error(
+            `[voice-call] Failed to start runtime: ${
+              err instanceof Error ? err.message : String(err)
+            }`,
+          );
+        }
+      },
+      stop: async () => {
+        if (!runtimePromise) return;
+        try {
+          const rt = await runtimePromise;
+          await rt.stop();
+        } finally {
+          runtimePromise = null;
+          runtime = null;
+        }
+      },
+    });
+  },
+};
+
+export default voiceCallPlugin;