Merge pull request #229 from pipecat-ai/khk-deepgram-url-configurable

Deepgram TTS service improvements

src/pipecat/services/deepgram.py

@@ -41,12 +41,14 @@ class DeepgramTTSService(TTSService):
             aiohttp_session: aiohttp.ClientSession,
             api_key: str,
             voice: str = "aura-helios-en",
+            base_url: str = "https://api.deepgram.com/v1/speak",
             **kwargs):
         super().__init__(**kwargs)
 
         self._voice = voice
         self._api_key = api_key
         self._aiohttp_session = aiohttp_session
+        self._base_url = base_url
 
     def can_generate_metrics(self) -> bool:
         return True
@@ -54,7 +56,7 @@ class DeepgramTTSService(TTSService):
     async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
         logger.debug(f"Generating TTS: [{text}]")
 
-        base_url = "https://api.deepgram.com/v1/speak"
+        base_url = self._base_url
         request_url = f"{base_url}?model={self._voice}&encoding=linear16&container=none&sample_rate=16000"
         headers = {"authorization": f"token {self._api_key}"}
         body = {"text": text}
@@ -63,9 +65,17 @@ class DeepgramTTSService(TTSService):
             await self.start_ttfb_metrics()
             async with self._aiohttp_session.post(request_url, headers=headers, json=body) as r:
                 if r.status != 200:
-                    text = await r.text()
-                    logger.error(f"Error getting audio (status: {r.status}, error: {text})")
-                    yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {text})")
+                    response_text = await r.text()
+                    # If we get a a "Bad Request: Input is unutterable", just print out a debug log.
+                    # All other unsuccesful requests should emit an error frame. If not specifically
+                    # handled by the running PipelineTask, the ErrorFrame will cancel the task.
+                    if "unutterable" in response_text:
+                        logger.debug(f"Unutterable text: [{text}]")
+                        return
+
+                    logger.error(
+                        f"Error getting audio (status: {r.status}, error: {response_text})")
+                    yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {response_text})")
                     return
 
                 async for data in r.content: