fix: voice_settings weren't applying to ElevenLabsTTSService

Fixed an issue with `GoogleSTTService` where it was constantly reconnecting

CHANGELOG.md

@@ -5,6 +5,22 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Fixed
+
+- Fixed an issue where `voice_settings` weren't being applied to
+  `ElevenLabsTTSService`.
+
+- Fixed an issue with `GoogleSTTService` where it was constantly reconnecting
+  before starting to receive audio from the user.
+
+- Fixed an issue where `GoogleLLMService`'s TTFB value was incorrect.
+
+### Other
+
+- Rename `14e-function-calling-gemini.py` to `14e-function-calling-google.py`.
+
 ## [0.0.71] - 2025-06-10
 
 ### Added

src/pipecat/services/elevenlabs/tts.py

@@ -140,6 +140,8 @@ def build_elevenlabs_voice_settings(
         if key in settings and settings[key] is not None:
             voice_settings[key] = settings[key]
 
+    print(f"Built voice settings: {voice_settings}")
+
     return voice_settings or None
 
 
@@ -249,6 +251,7 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
         return language_to_elevenlabs_language(language)
 
     def _set_voice_settings(self):
+        print(f"Setting voice settings for ElevenLabs TTS: {self._settings}")
         return build_elevenlabs_voice_settings(self._settings)
 
     async def set_model(self, model: str):
@@ -430,15 +433,20 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
     async def _send_text(self, text: str):
         if self._websocket:
             if not self._context_id:
+                # Create new context ID
+                new_context_id = str(uuid.uuid4())
+                # Register the context with the audio context manager
+                await self.create_audio_context(new_context_id)
+
                 # First message for a new context - need a space to initialize
-                msg = {"text": " ", "context_id": str(uuid.uuid4())}
+                msg = {"text": " ", "context_id": new_context_id}
 
                 # Add voice settings only in first message for a context
                 if self._voice_settings:
                     msg["voice_settings"] = self._voice_settings
 
                 await self._websocket.send(json.dumps(msg))
-                self._context_id = msg["context_id"]
+                self._context_id = new_context_id
                 logger.trace(f"Created new context {self._context_id}")
 
                 # Now send the actual text content
@@ -471,9 +479,6 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
                     yield TTSStartedFrame()
                     self._started = True
                     self._cumulative_time = 0
-                    # Create new context ID and register it
-                    self._context_id = str(uuid.uuid4())
-                    await self.create_audio_context(self._context_id)
 
                 await self._send_text(text)
                 await self.start_tts_usage_metrics(text)

src/pipecat/services/google/llm.py

@@ -555,10 +555,11 @@ class GoogleLLMService(LLMService):
                 contents=messages,
                 config=generation_config,
             )
-            await self.stop_ttfb_metrics()
 
             function_calls = []
             async for chunk in response:
+                # Stop TTFB metrics after the first chunk
+                await self.stop_ttfb_metrics()
                 if chunk.usage_metadata:
                     prompt_tokens += chunk.usage_metadata.prompt_token_count or 0
                     completion_tokens += chunk.usage_metadata.candidates_token_count or 0

src/pipecat/services/google/stt.py

@@ -747,6 +747,11 @@ class GoogleSTTService(STTService):
         try:
             while True:
                 try:
+                    if self._request_queue.empty():
+                        # wait for 10ms in case we don't have audio
+                        await asyncio.sleep(0.01)
+                        continue
+
                     # Start bi-directional streaming
                     streaming_recognize = await self._client.streaming_recognize(
                         requests=self._request_generator()