Stream audio in 4096-sample sub-chunks for immediate HA playback

Previously the entire synthesized audio for a sentence was sent as one
AudioChunk event. HA buffers until it arrives in full, so playback didn't
start until synthesis was complete. Splitting into 4096-sample chunks lets
HA begin playing as data arrives.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

wyoming_handler.py

@@ -135,16 +135,21 @@ class ChatterboxWyomingHandler(AsyncEventHandler):
                 continue
 
             audio_np = audio_tensor.cpu().numpy().squeeze()
-            audio_bytes = (audio_np * 32767).clip(-32768, 32767).astype(np.int16).tobytes()
+            audio_int16 = (audio_np * 32767).clip(-32768, 32767).astype(np.int16)
 
             if first_chunk:
                 ttfa = time.monotonic() - start_time
                 logger.info(f"Time to first audio: {ttfa:.3f}s")
                 first_chunk = False
 
+            # Send in small sub-chunks so HA can begin playback immediately
+            # rather than waiting for the full audio blob to arrive.
+            audio_chunk_samples = 4096
+            for offset in range(0, len(audio_int16), audio_chunk_samples):
+                sub = audio_int16[offset : offset + audio_chunk_samples]
                 await self.write_event(
                     AudioChunk(
-                    audio=audio_bytes,
+                        audio=sub.tobytes(),
                         rate=sample_rate,
                         width=2,
                         channels=1,