fix(voice-call): start listening after telnyx greetings

CHANGELOG.md

@@ -79,6 +79,7 @@ Docs: https://docs.openclaw.ai
 - Providers/ElevenLabs: omit the MP3-only `Accept` header for PCM telephony synthesis, so Voice Call requests for `pcm_22050` no longer receive MP3 audio. Fixes #67340. Thanks @marcchabot.
 - Plugins/Voice Call: reap stale pre-answer calls by default, honor configured TTS timeouts for Twilio media-stream playback, and fail empty telephony audio instead of completing as silence. Fixes #42071; supersedes #60957. Thanks @Ryce and @sliekens.
 - Plugins/Voice Call: terminate expired restored call sessions with the provider and restart restored max-duration timers with only the remaining duration, preventing stale outbound retry loops after Gateway restarts. Fixes #48739. Thanks @mira-solari.
+- Plugins/Voice Call: start provider STT after Telnyx outbound conversation greetings and pass configured Telnyx voice IDs through to the speak action. Fixes #56091. Thanks @Roshan.
 - Skills: honor legacy `metadata.clawdbot` requirements and installer hints when `metadata.openclaw` is absent, so older skills no longer appear ready when required binaries are missing. Fixes #71323. Thanks @chen-zhang-cs-code.
 - Browser/config: expand `~` in `browser.executablePath` before Chromium launch, so home-relative custom browser paths no longer fail with `ENOENT`. Fixes #67264. Thanks @Quratulain-bilal.
 - Telegram/streaming: hide tool-progress status updates by default while keeping explicit `streaming.preview.toolProgress` opt-in support for edited preview messages. Fixes #71320. Thanks @neeravmakwana.

extensions/voice-call/src/manager.notify.test.ts

@@ -245,6 +245,27 @@ describe("CallManager notify and mapping", () => {
     expectFirstPlayTtsText(provider, "Twilio stream unavailable");
   });
 
+  it("starts listening after the initial greeting for Telnyx conversation calls", async () => {
+    const { manager, provider } = await createManagerHarness({}, new FakeProvider("telnyx"));
+
+    const callId = await initiateCallWithMessage(
+      manager,
+      "+15550000012",
+      "Telnyx hello",
+      "conversation",
+    );
+    await answerCall(manager, callId, "evt-conversation-telnyx");
+
+    expectFirstPlayTtsText(provider, "Telnyx hello");
+    expect(provider.startListeningCalls).toEqual([
+      expect.objectContaining({
+        callId,
+        providerCallId: "call-uuid",
+      }),
+    ]);
+    expect(requireCall(manager, callId).state).toBe("listening");
+  });
+
   it("preserves initialMessage after a failed first playback and retries on next trigger", async () => {
     const provider = new FailFirstPlayTtsProvider("plivo");
     const { manager } = await createManagerHarness({}, provider);

extensions/voice-call/src/manager.test-harness.ts

@@ -19,7 +19,7 @@ import type {
 } from "./types.js";
 
 export class FakeProvider implements VoiceCallProvider {
-  readonly name: "plivo" | "twilio";
+  readonly name: "plivo" | "twilio" | "telnyx";
   twilioStreamConnectEnabled = true;
   readonly playTtsCalls: PlayTtsInput[] = [];
   readonly hangupCalls: HangupCallInput[] = [];
@@ -27,7 +27,7 @@ export class FakeProvider implements VoiceCallProvider {
   readonly stopListeningCalls: StopListeningInput[] = [];
   getCallStatusResult: GetCallStatusResult = { status: "in-progress", isTerminal: false };
 
-  constructor(name: "plivo" | "twilio" = "plivo") {
+  constructor(name: "plivo" | "twilio" | "telnyx" = "plivo") {
     this.name = name;
   }
 

extensions/voice-call/src/manager/outbound.test.ts

@@ -226,6 +226,36 @@ describe("voice-call outbound helpers", () => {
     expect(transitionStateMock).toHaveBeenLastCalledWith(call, "listening");
   });
 
+  it("passes configured voice ids through to Telnyx speak", async () => {
+    const call = { callId: "call-1", providerCallId: "provider-1", state: "active" };
+    const playTts = vi.fn(async () => {});
+    const ctx = {
+      activeCalls: new Map([["call-1", call]]),
+      providerCallIdMap: new Map(),
+      provider: { name: "telnyx", playTts },
+      config: {
+        tts: {
+          provider: "telnyx",
+          providers: {
+            telnyx: {
+              voiceId: "Telnyx.Qwen3TTS.12345678-1234-1234-1234-123456789abc",
+            },
+          },
+        },
+      },
+      storePath: "/tmp/voice-call.json",
+    };
+
+    await expect(speak(ctx as never, "call-1", "hello")).resolves.toEqual({ success: true });
+
+    expect(playTts).toHaveBeenCalledWith({
+      callId: "call-1",
+      providerCallId: "provider-1",
+      text: "hello",
+      voice: "Telnyx.Qwen3TTS.12345678-1234-1234-1234-123456789abc",
+    });
+  });
+
   it("sends DTMF through connected provider calls", async () => {
     const call = { callId: "call-1", providerCallId: "provider-1", state: "active" };
     const sendDtmfProvider = vi.fn(async () => {});

extensions/voice-call/src/manager/outbound.ts

@@ -213,7 +213,7 @@ export async function speak(
     transitionState(call, "speaking");
     persistCallRecord(ctx.storePath, call);
 
-    const voice = provider.name === "twilio" ? resolvePreferredTtsVoice(ctx.config) : undefined;
+    const voice = resolvePreferredTtsVoice(ctx.config);
     await provider.playTts({
       callId,
       providerCallId,
@@ -233,6 +233,19 @@ export async function speak(
   }
 }
 
+function shouldStartListeningAfterInitialMessage(ctx: ConversationContext): boolean {
+  if (ctx.provider?.name !== "twilio") {
+    return true;
+  }
+  if (!ctx.config.streaming.enabled) {
+    return true;
+  }
+  const streamAwareProvider = ctx.provider as typeof ctx.provider & {
+    isConversationStreamConnectEnabled?: () => boolean;
+  };
+  return streamAwareProvider.isConversationStreamConnectEnabled?.() !== true;
+}
+
 export async function sendDtmf(
   ctx: SpeakContext,
   callId: CallId,
@@ -316,6 +329,17 @@ export async function speakInitialMessage(
           await endCall(ctx, call.callId);
         }
       }, delaySec * 1000);
+    } else if (
+      mode === "conversation" &&
+      ctx.provider &&
+      shouldStartListeningAfterInitialMessage(ctx)
+    ) {
+      transitionState(call, "listening");
+      persistCallRecord(ctx.storePath, call);
+      await ctx.provider.startListening({
+        callId: call.callId,
+        providerCallId,
+      });
     }
   } finally {
     ctx.initialMessageInFlight.delete(call.callId);

extensions/voice-call/src/providers/telnyx.test.ts

@@ -301,3 +301,40 @@ describe("TelnyxProvider answer control", () => {
     expect(release).toHaveBeenCalledTimes(1);
   });
 });
+
+describe("TelnyxProvider speak control", () => {
+  it("passes custom Telnyx voice ids to the speak action", async () => {
+    const release = vi.fn(async () => {});
+    apiMocks.fetchWithSsrFGuard.mockResolvedValue({
+      response: new Response(JSON.stringify({ data: {} }), { status: 200 }),
+      release,
+    });
+    const provider = new TelnyxProvider({
+      apiKey: "KEY123",
+      connectionId: "CONN456",
+      publicKey: undefined,
+    });
+
+    await provider.playTts({
+      callId: "call-1",
+      providerCallId: "call-control-1",
+      text: "hello",
+      voice: "Telnyx.Qwen3TTS.12345678-1234-1234-1234-123456789abc",
+    });
+
+    expect(apiMocks.fetchWithSsrFGuard).toHaveBeenCalledWith(
+      expect.objectContaining({
+        url: "https://api.telnyx.com/v2/calls/call-control-1/actions/speak",
+        auditContext: "voice-call.telnyx.api",
+        policy: { allowedHostnames: ["api.telnyx.com"] },
+        init: expect.objectContaining({
+          method: "POST",
+          body: expect.stringContaining(
+            '"voice":"Telnyx.Qwen3TTS.12345678-1234-1234-1234-123456789abc"',
+          ),
+        }),
+      }),
+    );
+    expect(release).toHaveBeenCalledTimes(1);
+  });
+});