TTS service and example updates

examples/foundational/07i-interruptible-xtts.py

@@ -25,7 +25,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
-from pipecat.services.xtts.tts import XTTSService, XTTSSettings
+from pipecat.services.xtts.tts import XTTSService, XTTSTTSSettings
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = XTTSService(
             aiohttp_session=session,
-            settings=XTTSSettings(
+            settings=XTTSTTSSettings(
                 voice="Claribel Dervla",
             ),
             base_url="http://localhost:8000",

examples/foundational/07n-interruptible-gemini-image.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GoogleSTTService(
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
         settings=GoogleSTTSettings(
-            languages=Language.EN_US,
+            languages=[Language.EN_US],
         ),
     )
 

examples/foundational/07n-interruptible-gemini.py

@@ -55,7 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GoogleSTTService(
         settings=GoogleSTTSettings(
-            languages=Language.EN_US,
+            languages=[Language.EN_US],
         ),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )

examples/foundational/07n-interruptible-google-http.py

@@ -55,8 +55,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GoogleSTTService(
         settings=GoogleSTTSettings(
-            languages=Language.EN_US,
-            model="chirp_3",
+            languages=[Language.EN_US],
+            # Add model to use a specific model
+            # model="chirp_3",
         ),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
         location="us",

examples/foundational/07t-interruptible-fish.py

@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     tts = FishAudioTTSService(
         api_key=os.getenv("FISH_API_KEY"),
         settings=FishAudioTTSSettings(
-            model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+            voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
         ),
     )
 

examples/foundational/07z-interruptible-sarvam-http.py

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
-from pipecat.services.sarvam.stt import SarvamSTTService
+from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
 from pipecat.services.sarvam.tts import SarvamHttpTTSService, SarvamHttpTTSSettings
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -59,14 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SarvamSTTService(
             api_key=os.getenv("SARVAM_API_KEY"),
-            model="saarika:v2.5",
+            settings=SarvamSTTSettings(
+                model="saarika:v2.5",
+            ),
         )
 
         tts = SarvamHttpTTSService(
             api_key=os.getenv("SARVAM_API_KEY"),
             aiohttp_session=session,
             settings=SarvamHttpTTSSettings(
-                language=Language.EN,
+                language=Language.EN_IN,
             ),
         )
 

examples/foundational/15a-switch-languages.py

@@ -7,7 +7,6 @@
 
 import os
 
-from deepgram import LiveOptions
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -28,7 +27,7 @@ from pipecat.processors.filters.function_filter import FunctionFilter
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
-from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -102,7 +101,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = DeepgramSTTService(
-        api_key=os.getenv("DEEPGRAM_API_KEY"), live_options=LiveOptions(language="multi")
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramSTTSettings(
+            language="multi",
+        ),
     )
 
     tts = SwitchLanguage()