From e957cce422878be81b9f3888986d11203bde9158 Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Thu, 24 Oct 2024 13:42:06 -0400
Subject: [PATCH] Align TTSService constructors

---
 src/pipecat/services/cartesia.py   | 25 ++++++++++++-------------
 src/pipecat/services/elevenlabs.py |  8 ++++----
 2 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/src/pipecat/services/cartesia.py b/src/pipecat/services/cartesia.py
index 3d6111821..5ce0774de 100644
--- a/src/pipecat/services/cartesia.py
+++ b/src/pipecat/services/cartesia.py
@@ -68,9 +68,6 @@ def language_to_cartesia_language(language: Language) -> str | None:
 
 class CartesiaTTSService(WordTTSService):
     class InputParams(BaseModel):
-        encoding: Optional[str] = "pcm_s16le"
-        sample_rate: Optional[int] = 16000
-        container: Optional[str] = "raw"
         language: Optional[Language] = Language.EN
         speed: Optional[Union[str, float]] = ""
         emotion: Optional[List[str]] = []
@@ -83,6 +80,9 @@ class CartesiaTTSService(WordTTSService):
         cartesia_version: str = "2024-06-10",
         url: str = "wss://api.cartesia.ai/tts/websocket",
         model: str = "sonic-english",
+        sample_rate: int = 16000,
+        encoding: str = "pcm_s16le",
+        container: str = "raw",
         params: InputParams = InputParams(),
         **kwargs,
     ):
@@ -99,7 +99,6 @@ class CartesiaTTSService(WordTTSService):
         super().__init__(
             aggregate_sentences=True,
             push_text_frames=False,
-            sample_rate=params.sample_rate,
             **kwargs,
         )
 
@@ -108,9 +107,9 @@ class CartesiaTTSService(WordTTSService):
         self._url = url
         self._settings = {
             "output_format": {
-                "container": params.container,
-                "encoding": params.encoding,
-                "sample_rate": params.sample_rate,
+                "container": container,
+                "encoding": encoding,
+                "sample_rate": sample_rate,
             },
             "language": self.language_to_service_language(params.language)
             if params.language
@@ -288,9 +287,6 @@ class CartesiaTTSService(WordTTSService):
 
 class CartesiaHttpTTSService(TTSService):
     class InputParams(BaseModel):
-        encoding: Optional[str] = "pcm_s16le"
-        sample_rate: Optional[int] = 16000
-        container: Optional[str] = "raw"
         language: Optional[Language] = Language.EN
         speed: Optional[Union[str, float]] = ""
         emotion: Optional[List[str]] = []
@@ -302,6 +298,9 @@ class CartesiaHttpTTSService(TTSService):
         voice_id: str,
         model: str = "sonic-english",
         base_url: str = "https://api.cartesia.ai",
+        sample_rate: int = 16000,
+        encoding: str = "pcm_s16le",
+        container: str = "raw",
         params: InputParams = InputParams(),
         **kwargs,
     ):
@@ -310,9 +309,9 @@ class CartesiaHttpTTSService(TTSService):
         self._api_key = api_key
         self._settings = {
             "output_format": {
-                "container": params.container,
-                "encoding": params.encoding,
-                "sample_rate": params.sample_rate,
+                "container": container,
+                "encoding": encoding,
+                "sample_rate": sample_rate,
             },
             "language": self.language_to_service_language(params.language)
             if params.language
diff --git a/src/pipecat/services/elevenlabs.py b/src/pipecat/services/elevenlabs.py
index 708fa06c1..68441bfdf 100644
--- a/src/pipecat/services/elevenlabs.py
+++ b/src/pipecat/services/elevenlabs.py
@@ -74,7 +74,6 @@ def calculate_word_times(
 class ElevenLabsTTSService(WordTTSService):
     class InputParams(BaseModel):
         language: Optional[Language] = Language.EN
-        output_format: Literal["pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100"] = "pcm_16000"
         optimize_streaming_latency: Optional[str] = None
         stability: Optional[float] = None
         similarity_boost: Optional[float] = None
@@ -98,6 +97,7 @@ class ElevenLabsTTSService(WordTTSService):
         voice_id: str,
         model: str = "eleven_turbo_v2_5",
         url: str = "wss://api.elevenlabs.io",
+        output_format: Literal["pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100"] = "pcm_16000",
         params: InputParams = InputParams(),
         **kwargs,
     ):
@@ -120,18 +120,18 @@ class ElevenLabsTTSService(WordTTSService):
             push_text_frames=False,
             push_stop_frames=True,
             stop_frame_timeout_s=2.0,
-            sample_rate=sample_rate_from_output_format(params.output_format),
+            sample_rate=sample_rate_from_output_format(output_format),
             **kwargs,
         )
 
         self._api_key = api_key
         self._url = url
         self._settings = {
-            "sample_rate": sample_rate_from_output_format(params.output_format),
+            "sample_rate": sample_rate_from_output_format(output_format),
             "language": self.language_to_service_language(params.language)
             if params.language
             else Language.EN,
-            "output_format": params.output_format,
+            "output_format": output_format,
             "optimize_streaming_latency": params.optimize_streaming_latency,
             "stability": params.stability,
             "similarity_boost": params.similarity_boost,