diff --git a/javascript/src/voice/__tests__/interrupt-truncation.test.ts b/javascript/src/voice/__tests__/interrupt-truncation.test.ts
index 57c733965..6fa64811f 100644
--- a/javascript/src/voice/__tests__/interrupt-truncation.test.ts
+++ b/javascript/src/voice/__tests__/interrupt-truncation.test.ts
@@ -124,6 +124,30 @@ describe("defaultVoiceCall publishes the agent speaking event", () => {
     await expect(adapter.agentSpeakingEvent!.wait()).resolves.toBeUndefined();
   });
 
+  it("does not set the speaking event when the first chunk is empty", async () => {
+    const adapter = new SpeakingAdapter([
+      new AudioChunk({ data: new Uint8Array(0) }),
+    ]);
+
+    await defaultVoiceCall(adapter, bareInput);
+
+    expect(adapter.agentSpeakingEvent).toBeDefined();
+    expect(adapter.agentSpeakingEvent!.isSet()).toBe(false);
+  });
+
+  it("sets the speaking event when audio follows a leading empty chunk", async () => {
+    const adapter = new SpeakingAdapter([
+      new AudioChunk({ data: new Uint8Array(0) }),
+      tone(0.1, "after empty"),
+    ]);
+
+    await defaultVoiceCall(adapter, bareInput);
+
+    expect(adapter.agentSpeakingEvent).toBeDefined();
+    expect(adapter.agentSpeakingEvent!.isSet()).toBe(true);
+    await expect(adapter.agentSpeakingEvent!.wait()).resolves.toBeUndefined();
+  });
+
   it("clears the event at the start of the next turn (re-armed)", async () => {
     // Turn-2's first chunk is delayed so the cleared-but-not-yet-set window is
     // observable across a macrotask yield. Without it the immediate chunk would
diff --git a/javascript/src/voice/adapter.runtime.ts b/javascript/src/voice/adapter.runtime.ts
index 09c398fde..a8cf7511b 100644
--- a/javascript/src/voice/adapter.runtime.ts
+++ b/javascript/src/voice/adapter.runtime.ts
@@ -719,10 +719,16 @@ async function drainInner(
     "voice.audio.first_chunk_latency_ms",
     Math.round(performance.now() - receiveStart),
   );
-  if (first.data.length > 0) {
+  // The initial receive can be an empty prefix while the drain still yields
+  // audio. Publish speech on the first playable chunk wherever it appears.
+  let sawPlayableChunk = false;
+  const markFirstPlayableChunk = (chunk: AudioChunk): void => {
+    if (sawPlayableChunk || chunk.data.length === 0) return;
+    sawPlayableChunk = true;
     onFirstChunk();
-  }
-  speakingEvent.set();
+    speakingEvent.set();
+  };
+  markFirstPlayableChunk(first);
 
   const chunks: AudioChunk[] = [first];
   let accumulated = first.durationSeconds;
@@ -761,6 +767,7 @@ async function drainInner(
       terminatedReason = "terminal_chunk";
       break;
     }
+    markFirstPlayableChunk(next);
     chunks.push(next);
     accumulated += next.durationSeconds;
     maybeWarnSoftCap();