Merge pull request #2470 from pipecat-ai/mb/11labs-settings-reconnect

Update ElevenLabsTTSService: update runtime configuration

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- `ElevenLabsTTSService` now supports additional runtime changes to the `model`,
+  `language`, and `voice_settings` parameters.
+
 - Added `MistralLLMService`, using Mistral's chat completion API.
 
 - Added the ability to retry executing a chat completion after a timeout period

src/pipecat/services/elevenlabs/tts.py

@@ -370,13 +370,49 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
         await self._connect()
 
     async def _update_settings(self, settings: Mapping[str, Any]):
-        """Update service settings and reconnect if voice changed."""
+        """Update service settings and reconnect if voice, model, or language changed."""
+        # Track previous values for settings that require reconnection
         prev_voice = self._voice_id
+        prev_model = self.model_name
+        prev_language = self._settings.get("language")
+        # Create snapshot of current voice settings to detect changes after update
+        prev_voice_settings = self._voice_settings.copy() if self._voice_settings else None
+
         await super()._update_settings(settings)
-        if not prev_voice == self._voice_id:
+
-            logger.info(f"Switching TTS voice to: [{self._voice_id}]")
+        # Update voice settings for the next context creation
+        self._voice_settings = self._set_voice_settings()
+
+        # Check if URL-level settings changed (these require reconnection)
+        url_changed = (
+            prev_voice != self._voice_id
+            or prev_model != self.model_name
+            or prev_language != self._settings.get("language")
+        )
+
+        # Check if only voice settings changed (speed, stability, etc.)
+        voice_settings_changed = prev_voice_settings != self._voice_settings
+
+        if url_changed:
+            # These settings are in the WebSocket URL, so we need to reconnect
+            logger.debug(
+                f"URL-level setting changed (voice/model/language), reconnecting WebSocket"
+            )
             await self._disconnect()
             await self._connect()
+        elif voice_settings_changed and self._context_id:
+            # Voice settings can be updated by closing current context
+            # so new one gets created with updated voice settings
+            logger.debug(f"Voice settings changed, closing current context to apply changes")
+            try:
+                if self._websocket:
+                    await self._websocket.send(
+                        json.dumps({"context_id": self._context_id, "close_context": True})
+                    )
+            except Exception as e:
+                logger.warning(f"Error closing context for voice settings update: {e}")
+            self._context_id = None
+            self._started = False
 
     async def start(self, frame: StartFrame):
         """Start the ElevenLabs TTS service.

src/pipecat/services/tts_service.py

@@ -258,7 +258,7 @@ class TTSService(AIService):
                     self._settings[key] = self.language_to_service_language(value)
             elif key == "model":
                 self.set_model_name(value)
-            elif key == "voice":
+            elif key == "voice" or key == "voice_id":
                 self.set_voice(value)
             elif key == "text_filter":
                 for filter in self._text_filters: