diff --git a/src/pipecat/services/aws.py b/src/pipecat/services/aws.py
index 4a2eceab6..0ae72b968 100644
--- a/src/pipecat/services/aws.py
+++ b/src/pipecat/services/aws.py
@@ -121,7 +121,7 @@ class AWSTTSService(TTSService):
         self._settings = {
             "sample_rate": sample_rate,
             "engine": params.engine,
-            "language": language_to_aws_language(params.language) if params.language else "en-US",
+            "language": params.language if params.language else Language.EN,
             "pitch": params.pitch,
             "rate": params.rate,
             "volume": params.volume,
@@ -135,8 +135,8 @@ class AWSTTSService(TTSService):
     def _construct_ssml(self, text: str) -> str:
         ssml = "<speak>"
 
-        if self._settings["language"]:
-            ssml += f"<lang xml:lang='{self._settings['language']}'>"
+        language = language_to_aws_language(self._settings["language"])
+        ssml += f"<lang xml:lang='{language}'>"
 
         prosody_attrs = []
         # Prosody tags are only supported for standard and neural engines
@@ -158,8 +158,7 @@ class AWSTTSService(TTSService):
         if prosody_attrs:
             ssml += "</prosody>"
 
-        if self._settings["language"]:
-            ssml += "</lang>"
+        ssml += "</lang>"
 
         ssml += "</speak>"
 
diff --git a/src/pipecat/services/azure.py b/src/pipecat/services/azure.py
index eff5d333f..190a297a0 100644
--- a/src/pipecat/services/azure.py
+++ b/src/pipecat/services/azure.py
@@ -27,6 +27,7 @@ from pipecat.frames.frames import (
 )
 from pipecat.services.ai_services import ImageGenService, STTService, TTSService
 from pipecat.services.openai import BaseOpenAILLMService
+from pipecat.transcriptions import language
 from pipecat.transcriptions.language import Language
 from pipecat.utils.time import time_now_iso8601
 
@@ -191,7 +192,7 @@ class AzureTTSService(TTSService):
         self._settings = {
             "sample_rate": sample_rate,
             "emphasis": params.emphasis,
-            "language": language_to_azure_language(params.language) if params.language else "en-US",
+            "language": params.language if params.language else Language.EN,
             "pitch": params.pitch,
             "rate": params.rate,
             "role": params.role,
@@ -206,8 +207,9 @@ class AzureTTSService(TTSService):
         return True
 
     def _construct_ssml(self, text: str) -> str:
+        language = language_to_azure_language(self._settings["language"])
         ssml = (
-            f"<speak version='1.0' xml:lang='{self._settings['language']}' "
+            f"<speak version='1.0' xml:lang='{language}' "
             "xmlns='http://www.w3.org/2001/10/synthesis' "
             "xmlns:mstts='http://www.w3.org/2001/mstts'>"
             f"<voice name='{self._voice_id}'>"
diff --git a/src/pipecat/services/cartesia.py b/src/pipecat/services/cartesia.py
index 464c2d979..b8aab1161 100644
--- a/src/pipecat/services/cartesia.py
+++ b/src/pipecat/services/cartesia.py
@@ -106,7 +106,7 @@ class CartesiaTTSService(WordTTSService):
                 "encoding": params.encoding,
                 "sample_rate": params.sample_rate,
             },
-            "language": language_to_cartesia_language(params.language) if params.language else "en",
+            "language": params.language if params.language else Language.EN,
             "speed": params.speed,
             "emotion": params.emotion,
         }
@@ -146,7 +146,7 @@ class CartesiaTTSService(WordTTSService):
             "model_id": self.model_name,
             "voice": voice_config,
             "output_format": self._settings["output_format"],
-            "language": self._settings["language"],
+            "language": language_to_cartesia_language(self._settings["language"]),
             "add_timestamps": add_timestamps,
         }
         return json.dumps(msg)
@@ -303,7 +303,7 @@ class CartesiaHttpTTSService(TTSService):
                 "encoding": params.encoding,
                 "sample_rate": params.sample_rate,
             },
-            "language": language_to_cartesia_language(params.language) if params.language else None,
+            "language": params.language if params.language else Language.EN,
             "speed": params.speed,
             "emotion": params.emotion,
         }
@@ -343,7 +343,7 @@ class CartesiaHttpTTSService(TTSService):
                 transcript=text,
                 voice_id=self._voice_id,
                 output_format=self._settings["output_format"],
-                language=self._settings["language"],
+                language=language_to_cartesia_language(self._settings["language"]),
                 stream=False,
                 _experimental_voice_controls=voice_controls,
             )
diff --git a/src/pipecat/services/elevenlabs.py b/src/pipecat/services/elevenlabs.py
index 723e2f854..95ac5c1f1 100644
--- a/src/pipecat/services/elevenlabs.py
+++ b/src/pipecat/services/elevenlabs.py
@@ -198,9 +198,7 @@ class ElevenLabsTTSService(WordTTSService):
         self._url = url
         self._settings = {
             "sample_rate": sample_rate_from_output_format(params.output_format),
-            "language": language_to_elevenlabs_language(params.language)
-            if params.language
-            else "en",
+            "language": params.language if params.language else Language.EN,
             "output_format": params.output_format,
             "optimize_streaming_latency": params.optimize_streaming_latency,
             "stability": params.stability,
@@ -294,14 +292,14 @@ class ElevenLabsTTSService(WordTTSService):
             if self._settings["optimize_streaming_latency"]:
                 url += f"&optimize_streaming_latency={self._settings['optimize_streaming_latency']}"
 
-            # language can only be used with the 'eleven_turbo_v2_5' model
-            if self._settings["language"]:
-                if model == "eleven_turbo_v2_5":
-                    url += f"&language_code={self._settings['language']}"
-                else:
-                    logger.debug(
-                        f"Language code [{self._settings['language']}] not applied. Language codes can only be used with the 'eleven_turbo_v2_5' model."
-                    )
+            # Language can only be used with the 'eleven_turbo_v2_5' model
+            language = language_to_elevenlabs_language(self._settings["language"])
+            if model == "eleven_turbo_v2_5":
+                url += f"&language_code={language}"
+            else:
+                logger.debug(
+                    f"Language code [{language}] not applied. Language codes can only be used with the 'eleven_turbo_v2_5' model."
+                )
 
             self._websocket = await websockets.connect(url)
             self._receive_task = self.get_event_loop().create_task(self._receive_task_handler())
diff --git a/src/pipecat/services/gladia.py b/src/pipecat/services/gladia.py
index 8f270195b..e95329040 100644
--- a/src/pipecat/services/gladia.py
+++ b/src/pipecat/services/gladia.py
@@ -135,7 +135,7 @@ class GladiaSTTService(STTService):
         self._url = url
         self._settings = {
             "sample_rate": params.sample_rate,
-            "language": language_to_gladia_language(params.language) if params.language else "en",
+            "language": params.language if params.language else Language.EN,
             "transcription_hint": params.transcription_hint,
             "endpointing": params.endpointing,
             "prosody": params.prosody,
@@ -169,7 +169,7 @@ class GladiaSTTService(STTService):
             "model_type": "fast",
             "language_behaviour": "manual",
             "sample_rate": self._settings["sample_rate"],
-            "language": self._settings["language"],
+            "language": language_to_gladia_language(self._settings["language"]),
             "transcription_hint": self._settings["transcription_hint"],
             "endpointing": self._settings["endpointing"],
             "prosody": self._settings["prosody"],
diff --git a/src/pipecat/services/google.py b/src/pipecat/services/google.py
index a8187366a..93c2f2d62 100644
--- a/src/pipecat/services/google.py
+++ b/src/pipecat/services/google.py
@@ -40,7 +40,7 @@ try:
 except ModuleNotFoundError as e:
     logger.error(f"Exception: {e}")
     logger.error(
-        "In order to use Google AI, you need to `pip install pipecat-ai[google]`. Also, set `GOOGLE_APPLICATION_CREDENTIALS` environment variable."
+        "In order to use Google AI, you need to `pip install pipecat-ai[google]`. Also, set the environment variable GOOGLE_API_KEY for the GoogleLLMService and GOOGLE_APPLICATION_CREDENTIALS for the GoogleTTSService`."
     )
     raise Exception(f"Missing module: {e}")
 
@@ -261,9 +261,7 @@ class GoogleTTSService(TTSService):
             "rate": params.rate,
             "volume": params.volume,
             "emphasis": params.emphasis,
-            "language": language_to_google_language(params.language)
-            if params.language
-            else "en-US",
+            "language": params.language if params.language else Language.EN,
             "gender": params.gender,
             "google_style": params.google_style,
         }
@@ -298,8 +296,10 @@ class GoogleTTSService(TTSService):
 
         # Voice tag
         voice_attrs = [f"name='{self._voice_id}'"]
-        if self._settings["language"]:
-            voice_attrs.append(f"language='{self._settings['language']}'")
+
+        language = language_to_google_language(self._settings["language"])
+        voice_attrs.append(f"language='{language}'")
+
         if self._settings["gender"]:
             voice_attrs.append(f"gender='{self._settings['gender']}'")
         ssml += f"<voice {' '.join(voice_attrs)}>"
diff --git a/src/pipecat/services/lmnt.py b/src/pipecat/services/lmnt.py
index eea4fd9db..8f7fe6528 100644
--- a/src/pipecat/services/lmnt.py
+++ b/src/pipecat/services/lmnt.py
@@ -82,7 +82,7 @@ class LmntTTSService(TTSService):
                 "encoding": "pcm_s16le",
                 "sample_rate": sample_rate,
             },
-            "language": language_to_lmnt_language(language) if language else "en",
+            "language": language,
         }
 
         self.set_voice(voice_id)
diff --git a/src/pipecat/services/xtts.py b/src/pipecat/services/xtts.py
index d3cea254a..2f842c896 100644
--- a/src/pipecat/services/xtts.py
+++ b/src/pipecat/services/xtts.py
@@ -94,7 +94,7 @@ class XTTSService(TTSService):
         super().__init__(**kwargs)
 
         self._settings = {
-            "language": language_to_xtts_language(language) if language else "en",
+            "language": language,
             "base_url": base_url,
         }
         self.set_voice(voice_id)
@@ -131,9 +131,11 @@ class XTTSService(TTSService):
 
         url = self._settings["base_url"] + "/tts_stream"
 
+        language = language_to_xtts_language(self._settings["language"])
+
         payload = {
             "text": text.replace(".", "").replace("*", ""),
-            "language": self._settings["language"],
+            "language": language,
             "speaker_embedding": embeddings["speaker_embedding"],
             "gpt_cond_latent": embeddings["gpt_cond_latent"],
             "add_wav_header": False,