Merge pull request #1524 from pipecat-ai/mb/tts-generate-with-text

TTS: Skip generation when there is no text

src/pipecat/services/cartesia/tts.py

@@ -158,7 +158,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
                 voice_config["__experimental_controls"]["emotion"] = self._settings["emotion"]
 
         msg = {
-            "transcript": text or " ",  # Text must contain at least one character
+            "transcript": text,
             "continue": continue_transcript,
             "context_id": self._context_id,
             "model_id": self.model_name,
@@ -287,7 +287,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
                 self._context_id = str(uuid.uuid4())
                 await self.create_audio_context(self._context_id)
 
-            msg = self._build_msg(text=text or " ")  # Text must contain at least one character
+            msg = self._build_msg(text=text)
 
             try:
                 await self._get_websocket().send(msg)

src/pipecat/services/openai/tts.py

@@ -105,7 +105,7 @@ class OpenAITTSService(TTSService):
                 extra_body["instructions"] = self._instructions
 
             async with self._client.audio.speech.with_streaming_response.create(
-                input=text or " ",  # Text must contain at least one character
+                input=text,
                 model=self.model_name,
                 voice=VALID_VOICES[self._voice_id],
                 response_format="pcm",

src/pipecat/services/tts_service.py

@@ -269,7 +269,8 @@ class TTSService(AIService):
             filter.reset_interruption()
             text = filter.filter(text)
 
-        await self.process_generator(self.run_tts(text))
+        if text:
+            await self.process_generator(self.run_tts(text))
 
         await self.stop_processing_metrics()