Tidying up the Hume example and service

CHANGELOG.md

@@ -9,9 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
-- Added `HumeTTSService` for text-to-speech synthesis using Hume AI's expressive voice models.
-  Provides high-quality, emotionally expressive speech synthesis with support for various voice models.
-  Includes example in `examples/foundational/07ad-interruptible-hume.py`.
+- Added `HumeTTSService` for text-to-speech synthesis using Hume AI's
+  expressive voice models. Provides high-quality, emotionally expressive speech
+  synthesis with support for various voice models. Includes example in
+  `examples/foundational/07ad-interruptible-hume.py`.
 
 - Added `hume` optional dependency group for Hume AI TTS integration.
 

examples/foundational/07ae-interruptible-hume.py

@@ -7,7 +7,12 @@
 import os
 
 from dotenv import load_dotenv
+from loguru import logger
 
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -32,14 +37,21 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
-    "webrtc": lambda: TransportParams(),
 }
 
 
@@ -108,7 +120,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 async def bot(runner_args: RunnerArguments):
     """Main bot entry point compatible with Pipecat Cloud."""
     transport = await create_transport(runner_args, transport_params)
-
     await run_bot(transport, runner_args)
 
 

src/pipecat/services/hume/tts.py

@@ -201,12 +201,20 @@ class HumeTTSService(TTSService):
                 if len(self._audio_bytes) < self.chunk_size:
                     continue
 
-                yield TTSAudioRawFrame(self._audio_bytes, self.sample_rate, 1)
+                frame = TTSAudioRawFrame(
+                    audio=self._audio_bytes,
+                    sample_rate=self.sample_rate,
+                    num_channels=1,
+                )
+
+                yield frame
+
                 self._audio_bytes = b""
 
         except Exception as e:
             logger.exception(f"{self} error generating TTS: {e}")
-            yield ErrorFrame(error=str(e))
+            await self.push_error(ErrorFrame(f"Error generating TTS: {e}"))
         finally:
             # Ensure TTFB timer is stopped even on early failures
+            await self.stop_ttfb_metrics()
             yield TTSStoppedFrame()