Satisfy minimal text requirements for Cartesia and OpenAI

src/pipecat/services/cartesia.py

@@ -152,7 +152,7 @@ class CartesiaTTSService(WordTTSService):
                 voice_config["__experimental_controls"]["emotion"] = self._settings["emotion"]
 
         msg = {
-            "transcript": text,
+            "transcript": text or " ",  # Text must contain at least one character
             "continue": continue_transcript,
             "context_id": self._context_id,
             "model_id": self.model_name,
@@ -271,7 +271,7 @@ class CartesiaTTSService(WordTTSService):
                 yield TTSStartedFrame()
                 self._context_id = str(uuid.uuid4())
 
-            msg = self._build_msg(text=text)
+            msg = self._build_msg(text=text or " ")  # Text must contain at least one character
 
             try:
                 await self._get_websocket().send(msg)

src/pipecat/services/openai.py

@@ -409,7 +409,7 @@ class OpenAITTSService(TTSService):
             await self.start_ttfb_metrics()
 
             async with self._client.audio.speech.with_streaming_response.create(
-                input=text,
+                input=text or " ",  # Text must contain at least one character
                 model=self.model_name,
                 voice=VALID_VOICES[self._voice_id],
                 response_format="pcm",

src/pipecat/utils/text/markdown_text_filter.py

@@ -96,7 +96,7 @@ class MarkdownTextFilter(BaseTextFilter):
             # Restore leading and trailing spaces
             filtered_text = re.sub("§", " ", filtered_text)
 
-            return filtered_text or " "  # Return a space to satisfy TTS services
+            return filtered_text
         else:
             return text