Merge pull request #1197 from pipecat-ai/mb/google-stt

Add GoogleSTTService
2025-02-12 10:16:18 -05:00
parent e2b4554a54 5d6370690c
commit 24cdcd74e6
5 changed files with 791 additions and 18 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ### Added

+- Added support for Google Cloud Speech-to-Text V2 through `GoogleSTTService`.
+
 - Added `RimeTTSService`, a new `WordTTSService`. Updated the foundational
  example `07q-interruptible-rime.py` to use `RimeTTSService`.

@@ -21,10 +23,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
  OpenAI-compatible interface. Also, added foundational example
  `14n-function-calling-perplexity.py`.

- Added `DailyTransport.update_remote_participants()`. This allows you to update remote participant's settings, like their permissions or which of their devices are enabled. Requires that the local participant have participant admin permission.
+- Added `DailyTransport.update_remote_participants()`. This allows you to
+  update remote participant's settings, like their permissions or which of
+  their devices are enabled. Requires that the local participant have
+  participant admin permission.

 ### Changed

+- Updated foundational example `07n-interruptible-google.py` to use all Google
+  services.
+
 - `RimeHttpTTSService` now uses the `mistv2` model by default.

 - Improved error handling in `AzureTTSService` to properly detect and log
@@ -40,7 +48,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
  model.

 - `RTVIObserver` doesn't handle `LLMSearchResponseFrame` frames anymore. For
-  now, to handle those frames you need to create a `GoogleRTVIObserver` instead.
+  now, to handle those frames you need to create a `GoogleRTVIObserver`
+  instead.

 ### Deprecated

@@ -63,8 +72,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an `RTVI` issue that was causing `bot-tts-text` messages to be sent
  before being processed by the output transport.

- Fixed an issue[#1192] in 11labs where we are trying to reconnect/disconnect the
-  websocket connection even when the connection is already closed.
+- Fixed an issue[#1192] in 11labs where we are trying to reconnect/disconnect
+  the websocket connection even when the connection is already closed.

 ## [0.0.56] - 2025-02-06

@@ -85,7 +94,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
  logging setup.

 - Fixed a `SentryMetrics` issue that was preventing any metrics to be sent to
-  Sentry and also was preventing from metrics frames to be pushed to the pipeline.
+  Sentry and also was preventing from metrics frames to be pushed to the
+  pipeline.

 - Fixed an issue in `BaseOutputTransport` where incoming audio would not be
  resampled to the desired output sample rate.
--- a/README.md
+++ b/README.md
@@ -57,7 +57,7 @@ pip install "pipecat-ai[option,...]"

 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | Install Command Example                 |
 | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `pip install "pipecat-ai[deepgram]"`    |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[deepgram]"`    |
 | LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
 | Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                                                                                                                                                                          | `pip install "pipecat-ai[cartesia]"`    |
 | Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[google]"`      |
--- a/examples/foundational/07n-interruptible-google.py
+++ b/examples/foundational/07n-interruptible-google.py
@@ -18,9 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.deepgram import DeepgramSTTService
-from pipecat.services.google import GoogleTTSService
-from pipecat.services.openai import OpenAILLMService
+from pipecat.services.google import GoogleLLMService, GoogleSTTService, GoogleTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport

@@ -46,14 +44,16 @@ async def main():
            ),
        )

-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = GoogleSTTService(
+            params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        )

        tts = GoogleTTSService(
            voice_id="en-US-Journey-F",
            params=GoogleTTSService.InputParams(language=Language.EN_US),
        )

-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))

        messages = [
            {
--- a/src/pipecat/services/google/google.py
+++ b/src/pipecat/services/google/google.py
@@ -8,24 +8,35 @@ import asyncio
 import base64
 import io
 import json
+import os
+import time
+
+# Suppress gRPC fork warnings
+os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
+
 from dataclasses import dataclass
-from typing import Any, AsyncGenerator, Dict, List, Literal, Optional
+from typing import Any, AsyncGenerator, Dict, List, Literal, Optional, Union

 from loguru import logger
 from PIL import Image
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator

 from pipecat.frames.frames import (
    AudioRawFrame,
+    CancelFrame,
+    EndFrame,
    ErrorFrame,
    Frame,
    FunctionCallResultProperties,
+    InterimTranscriptionFrame,
    LLMFullResponseEndFrame,
    LLMFullResponseStartFrame,
    LLMMessagesFrame,
    LLMTextFrame,
    LLMUpdateSettingsFrame,
    OpenAILLMContextAssistantTimestampFrame,
+    StartFrame,
+    TranscriptionFrame,
    TTSAudioRawFrame,
    TTSStartedFrame,
    TTSStoppedFrame,
@@ -38,7 +49,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
    OpenAILLMContextFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.ai_services import ImageGenService, LLMService, TTSService
+from pipecat.services.ai_services import ImageGenService, LLMService, STTService, TTSService
 from pipecat.services.google.frames import LLMSearchResponseFrame
 from pipecat.services.openai import (
    OpenAIAssistantContextAggregator,
@@ -51,10 +62,13 @@ try:
    import google.ai.generativelanguage as glm
    import google.generativeai as gai
    from google import genai
-    from google.cloud import texttospeech_v1
+    from google.api_core.client_options import ClientOptions
+    from google.cloud import speech_v2, texttospeech_v1
+    from google.cloud.speech_v2.types import cloud_speech
    from google.genai import types
    from google.generativeai.types import GenerationConfig
    from google.oauth2 import service_account
+
 except ModuleNotFoundError as e:
    logger.error(f"Exception: {e}")
    logger.error(
@@ -63,7 +77,7 @@ except ModuleNotFoundError as e:
    raise Exception(f"Missing module: {e}")


-def language_to_google_language(language: Language) -> Optional[str]:
+def language_to_google_tts_language(language: Language) -> Optional[str]:
    language_map = {
        # Afrikaans
        Language.AF: "af-ZA",
@@ -223,6 +237,305 @@ def language_to_google_language(language: Language) -> Optional[str]:
    return language_map.get(language)


+def language_to_google_stt_language(language: Language) -> Optional[str]:
+    """Maps Language enum to Google Speech-to-Text V2 language codes.
+
+    Args:
+        language: Language enum value.
+
+    Returns:
+        Optional[str]: Google STT language code or None if not supported.
+    """
+    language_map = {
+        # Afrikaans
+        Language.AF: "af-ZA",
+        Language.AF_ZA: "af-ZA",
+        # Albanian
+        Language.SQ: "sq-AL",
+        Language.SQ_AL: "sq-AL",
+        # Amharic
+        Language.AM: "am-ET",
+        Language.AM_ET: "am-ET",
+        # Arabic
+        Language.AR: "ar-EG",  # Default to Egypt
+        Language.AR_AE: "ar-AE",
+        Language.AR_BH: "ar-BH",
+        Language.AR_DZ: "ar-DZ",
+        Language.AR_EG: "ar-EG",
+        Language.AR_IQ: "ar-IQ",
+        Language.AR_JO: "ar-JO",
+        Language.AR_KW: "ar-KW",
+        Language.AR_LB: "ar-LB",
+        Language.AR_MA: "ar-MA",
+        Language.AR_OM: "ar-OM",
+        Language.AR_QA: "ar-QA",
+        Language.AR_SA: "ar-SA",
+        Language.AR_SY: "ar-SY",
+        Language.AR_TN: "ar-TN",
+        Language.AR_YE: "ar-YE",
+        # Armenian
+        Language.HY: "hy-AM",
+        Language.HY_AM: "hy-AM",
+        # Azerbaijani
+        Language.AZ: "az-AZ",
+        Language.AZ_AZ: "az-AZ",
+        # Basque
+        Language.EU: "eu-ES",
+        Language.EU_ES: "eu-ES",
+        # Bengali
+        Language.BN: "bn-IN",  # Default to India
+        Language.BN_BD: "bn-BD",
+        Language.BN_IN: "bn-IN",
+        # Bosnian
+        Language.BS: "bs-BA",
+        Language.BS_BA: "bs-BA",
+        # Bulgarian
+        Language.BG: "bg-BG",
+        Language.BG_BG: "bg-BG",
+        # Burmese
+        Language.MY: "my-MM",
+        Language.MY_MM: "my-MM",
+        # Catalan
+        Language.CA: "ca-ES",
+        Language.CA_ES: "ca-ES",
+        # Chinese
+        Language.ZH: "cmn-Hans-CN",  # Default to Simplified Chinese
+        Language.ZH_CN: "cmn-Hans-CN",
+        Language.ZH_HK: "cmn-Hans-HK",
+        Language.ZH_TW: "cmn-Hant-TW",
+        Language.YUE: "yue-Hant-HK",  # Cantonese
+        Language.YUE_CN: "yue-Hant-HK",
+        # Croatian
+        Language.HR: "hr-HR",
+        Language.HR_HR: "hr-HR",
+        # Czech
+        Language.CS: "cs-CZ",
+        Language.CS_CZ: "cs-CZ",
+        # Danish
+        Language.DA: "da-DK",
+        Language.DA_DK: "da-DK",
+        # Dutch
+        Language.NL: "nl-NL",  # Default to Netherlands
+        Language.NL_BE: "nl-BE",
+        Language.NL_NL: "nl-NL",
+        # English
+        Language.EN: "en-US",  # Default to US
+        Language.EN_AU: "en-AU",
+        Language.EN_CA: "en-CA",
+        Language.EN_GB: "en-GB",
+        Language.EN_GH: "en-GH",
+        Language.EN_HK: "en-HK",
+        Language.EN_IN: "en-IN",
+        Language.EN_IE: "en-IE",
+        Language.EN_KE: "en-KE",
+        Language.EN_NG: "en-NG",
+        Language.EN_NZ: "en-NZ",
+        Language.EN_PH: "en-PH",
+        Language.EN_SG: "en-SG",
+        Language.EN_TZ: "en-TZ",
+        Language.EN_US: "en-US",
+        Language.EN_ZA: "en-ZA",
+        # Estonian
+        Language.ET: "et-EE",
+        Language.ET_EE: "et-EE",
+        # Filipino
+        Language.FIL: "fil-PH",
+        Language.FIL_PH: "fil-PH",
+        # Finnish
+        Language.FI: "fi-FI",
+        Language.FI_FI: "fi-FI",
+        # French
+        Language.FR: "fr-FR",  # Default to France
+        Language.FR_BE: "fr-BE",
+        Language.FR_CA: "fr-CA",
+        Language.FR_CH: "fr-CH",
+        Language.FR_FR: "fr-FR",
+        # Galician
+        Language.GL: "gl-ES",
+        Language.GL_ES: "gl-ES",
+        # Georgian
+        Language.KA: "ka-GE",
+        Language.KA_GE: "ka-GE",
+        # German
+        Language.DE: "de-DE",  # Default to Germany
+        Language.DE_AT: "de-AT",
+        Language.DE_CH: "de-CH",
+        Language.DE_DE: "de-DE",
+        # Greek
+        Language.EL: "el-GR",
+        Language.EL_GR: "el-GR",
+        # Gujarati
+        Language.GU: "gu-IN",
+        Language.GU_IN: "gu-IN",
+        # Hebrew
+        Language.HE: "iw-IL",
+        Language.HE_IL: "iw-IL",
+        # Hindi
+        Language.HI: "hi-IN",
+        Language.HI_IN: "hi-IN",
+        # Hungarian
+        Language.HU: "hu-HU",
+        Language.HU_HU: "hu-HU",
+        # Icelandic
+        Language.IS: "is-IS",
+        Language.IS_IS: "is-IS",
+        # Indonesian
+        Language.ID: "id-ID",
+        Language.ID_ID: "id-ID",
+        # Italian
+        Language.IT: "it-IT",
+        Language.IT_IT: "it-IT",
+        Language.IT_CH: "it-CH",
+        # Japanese
+        Language.JA: "ja-JP",
+        Language.JA_JP: "ja-JP",
+        # Javanese
+        Language.JV: "jv-ID",
+        Language.JV_ID: "jv-ID",
+        # Kannada
+        Language.KN: "kn-IN",
+        Language.KN_IN: "kn-IN",
+        # Kazakh
+        Language.KK: "kk-KZ",
+        Language.KK_KZ: "kk-KZ",
+        # Khmer
+        Language.KM: "km-KH",
+        Language.KM_KH: "km-KH",
+        # Korean
+        Language.KO: "ko-KR",
+        Language.KO_KR: "ko-KR",
+        # Lao
+        Language.LO: "lo-LA",
+        Language.LO_LA: "lo-LA",
+        # Latvian
+        Language.LV: "lv-LV",
+        Language.LV_LV: "lv-LV",
+        # Lithuanian
+        Language.LT: "lt-LT",
+        Language.LT_LT: "lt-LT",
+        # Macedonian
+        Language.MK: "mk-MK",
+        Language.MK_MK: "mk-MK",
+        # Malay
+        Language.MS: "ms-MY",
+        Language.MS_MY: "ms-MY",
+        # Malayalam
+        Language.ML: "ml-IN",
+        Language.ML_IN: "ml-IN",
+        # Marathi
+        Language.MR: "mr-IN",
+        Language.MR_IN: "mr-IN",
+        # Mongolian
+        Language.MN: "mn-MN",
+        Language.MN_MN: "mn-MN",
+        # Nepali
+        Language.NE: "ne-NP",
+        Language.NE_NP: "ne-NP",
+        # Norwegian
+        Language.NO: "no-NO",
+        Language.NB: "no-NO",
+        Language.NB_NO: "no-NO",
+        # Persian
+        Language.FA: "fa-IR",
+        Language.FA_IR: "fa-IR",
+        # Polish
+        Language.PL: "pl-PL",
+        Language.PL_PL: "pl-PL",
+        # Portuguese
+        Language.PT: "pt-PT",  # Default to Portugal
+        Language.PT_BR: "pt-BR",
+        Language.PT_PT: "pt-PT",
+        # Punjabi
+        Language.PA: "pa-Guru-IN",
+        Language.PA_IN: "pa-Guru-IN",
+        # Romanian
+        Language.RO: "ro-RO",
+        Language.RO_RO: "ro-RO",
+        # Russian
+        Language.RU: "ru-RU",
+        Language.RU_RU: "ru-RU",
+        # Serbian
+        Language.SR: "sr-RS",
+        Language.SR_RS: "sr-RS",
+        # Sinhala
+        Language.SI: "si-LK",
+        Language.SI_LK: "si-LK",
+        # Slovak
+        Language.SK: "sk-SK",
+        Language.SK_SK: "sk-SK",
+        # Slovenian
+        Language.SL: "sl-SI",
+        Language.SL_SI: "sl-SI",
+        # Spanish
+        Language.ES: "es-ES",  # Default to Spain
+        Language.ES_AR: "es-AR",
+        Language.ES_BO: "es-BO",
+        Language.ES_CL: "es-CL",
+        Language.ES_CO: "es-CO",
+        Language.ES_CR: "es-CR",
+        Language.ES_DO: "es-DO",
+        Language.ES_EC: "es-EC",
+        Language.ES_ES: "es-ES",
+        Language.ES_GT: "es-GT",
+        Language.ES_HN: "es-HN",
+        Language.ES_MX: "es-MX",
+        Language.ES_NI: "es-NI",
+        Language.ES_PA: "es-PA",
+        Language.ES_PE: "es-PE",
+        Language.ES_PR: "es-PR",
+        Language.ES_PY: "es-PY",
+        Language.ES_SV: "es-SV",
+        Language.ES_US: "es-US",
+        Language.ES_UY: "es-UY",
+        Language.ES_VE: "es-VE",
+        # Sundanese
+        Language.SU: "su-ID",
+        Language.SU_ID: "su-ID",
+        # Swahili
+        Language.SW: "sw-TZ",  # Default to Tanzania
+        Language.SW_KE: "sw-KE",
+        Language.SW_TZ: "sw-TZ",
+        # Swedish
+        Language.SV: "sv-SE",
+        Language.SV_SE: "sv-SE",
+        # Tamil
+        Language.TA: "ta-IN",  # Default to India
+        Language.TA_IN: "ta-IN",
+        Language.TA_MY: "ta-MY",
+        Language.TA_SG: "ta-SG",
+        Language.TA_LK: "ta-LK",
+        # Telugu
+        Language.TE: "te-IN",
+        Language.TE_IN: "te-IN",
+        # Thai
+        Language.TH: "th-TH",
+        Language.TH_TH: "th-TH",
+        # Turkish
+        Language.TR: "tr-TR",
+        Language.TR_TR: "tr-TR",
+        # Ukrainian
+        Language.UK: "uk-UA",
+        Language.UK_UA: "uk-UA",
+        # Urdu
+        Language.UR: "ur-IN",  # Default to India
+        Language.UR_IN: "ur-IN",
+        Language.UR_PK: "ur-PK",
+        # Uzbek
+        Language.UZ: "uz-UZ",
+        Language.UZ_UZ: "uz-UZ",
+        # Vietnamese
+        Language.VI: "vi-VN",
+        Language.VI_VN: "vi-VN",
+        # Xhosa
+        Language.XH: "xh-ZA",
+        # Zulu
+        Language.ZU: "zu-ZA",
+        Language.ZU_ZA: "zu-ZA",
+    }
+
+    return language_map.get(language)
+
+
 class GoogleUserContextAggregator(OpenAIUserContextAggregator):
    async def _push_aggregation(self):
        if len(self._aggregation) > 0:
@@ -621,7 +934,7 @@ class GoogleLLMContext(OpenAILLMContext):


 class GoogleLLMService(LLMService):
-    """This class implements inference with Google's AI models
+    """This class implements inference with Google's AI models.

    This service translates internally from OpenAILLMContext to the messages format
    expected by the Google AI model. We are using the OpenAILLMContext as a lingua
@@ -927,7 +1240,7 @@ class GoogleTTSService(TTSService):
        return True

    def language_to_service_language(self, language: Language) -> Optional[str]:
-        return language_to_google_language(language)
+        return language_to_google_tts_language(language)

    def _construct_ssml(self, text: str) -> str:
        ssml = "<speak>"
@@ -1097,3 +1410,451 @@ class GoogleImageGenService(ImageGenService):
        except Exception as e:
            logger.error(f"{self} error generating image: {e}")
            yield ErrorFrame(f"Image generation error: {str(e)}")
+
+
+class GoogleSTTService(STTService):
+    """Google Cloud Speech-to-Text V2 service implementation.
+
+    Provides real-time speech recognition using Google Cloud's Speech-to-Text V2 API
+    with streaming support. Handles audio transcription and optional voice activity detection.
+
+    Attributes:
+        InputParams: Configuration parameters for the STT service.
+    """
+
+    # Google Cloud's STT service has a connection time limit of 5 minutes per stream.
+    # They've shared an "endless streaming" example that guided this implementation:
+    # https://cloud.google.com/speech-to-text/docs/transcribe-streaming-audio#endless-streaming
+
+    STREAMING_LIMIT = 240000  # 4 minutes in milliseconds
+
+    class InputParams(BaseModel):
+        """Configuration parameters for Google Speech-to-Text.
+
+        Attributes:
+            languages: Single language or list of recognition languages. First language is primary.
+            model: Speech recognition model to use.
+            use_separate_recognition_per_channel: Process each audio channel separately.
+            enable_automatic_punctuation: Add punctuation to transcripts.
+            enable_spoken_punctuation: Include spoken punctuation in transcript.
+            enable_spoken_emojis: Include spoken emojis in transcript.
+            profanity_filter: Filter profanity from transcript.
+            enable_word_time_offsets: Include timing information for each word.
+            enable_word_confidence: Include confidence scores for each word.
+            enable_interim_results: Stream partial recognition results.
+            enable_voice_activity_events: Detect voice activity in audio.
+        """
+
+        languages: Union[Language, List[Language]] = Field(default_factory=lambda: [Language.EN_US])
+        model: Optional[str] = "latest_long"
+        use_separate_recognition_per_channel: Optional[bool] = False
+        enable_automatic_punctuation: Optional[bool] = True
+        enable_spoken_punctuation: Optional[bool] = False
+        enable_spoken_emojis: Optional[bool] = False
+        profanity_filter: Optional[bool] = False
+        enable_word_time_offsets: Optional[bool] = False
+        enable_word_confidence: Optional[bool] = False
+        enable_interim_results: Optional[bool] = True
+        enable_voice_activity_events: Optional[bool] = False
+
+        @field_validator("languages", mode="before")
+        @classmethod
+        def validate_languages(cls, v) -> List[Language]:
+            if isinstance(v, Language):
+                return [v]
+            return v
+
+        @property
+        def language_list(self) -> List[Language]:
+            """Get languages as a guaranteed list."""
+            assert isinstance(self.languages, list)
+            return self.languages
+
+    def __init__(
+        self,
+        *,
+        credentials: Optional[str] = None,
+        credentials_path: Optional[str] = None,
+        location: str = "global",
+        sample_rate: Optional[int] = None,
+        params: InputParams = InputParams(),
+        **kwargs,
+    ):
+        """Initialize the Google STT service.
+
+        Args:
+            credentials: JSON string containing Google Cloud service account credentials.
+            credentials_path: Path to service account credentials JSON file.
+            location: Google Cloud location (e.g., "global", "us-central1").
+            sample_rate: Audio sample rate in Hertz.
+            params: Configuration parameters for the service.
+            **kwargs: Additional arguments passed to STTService.
+
+        Raises:
+            ValueError: If neither credentials nor credentials_path is provided.
+            ValueError: If project ID is not found in credentials.
+        """
+        super().__init__(sample_rate=sample_rate, **kwargs)
+
+        self._location = location
+        self._stream = None
+        self._config = None
+        self._request_queue = asyncio.Queue()
+        self._streaming_task = None
+
+        # Used for keep-alive logic
+        self._stream_start_time = 0
+        self._last_audio_input = []
+        self._audio_input = []
+        self._result_end_time = 0
+        self._is_final_end_time = 0
+        self._final_request_end_time = 0
+        self._bridging_offset = 0
+        self._last_transcript_was_final = False
+        self._new_stream = True
+        self._restart_counter = 0
+
+        # Configure client options based on location
+        client_options = None
+        if self._location != "global":
+            client_options = ClientOptions(api_endpoint=f"{self._location}-speech.googleapis.com")
+
+        # Extract project ID and create client
+        if credentials:
+            json_account_info = json.loads(credentials)
+            self._project_id = json_account_info.get("project_id")
+            creds = service_account.Credentials.from_service_account_info(json_account_info)
+        elif credentials_path:
+            with open(credentials_path) as f:
+                json_account_info = json.load(f)
+                self._project_id = json_account_info.get("project_id")
+            creds = service_account.Credentials.from_service_account_file(credentials_path)
+        else:
+            raise ValueError("Either credentials or credentials_path must be provided")
+
+        if not self._project_id:
+            raise ValueError("Project ID not found in credentials")
+
+        self._client = speech_v2.SpeechAsyncClient(credentials=creds, client_options=client_options)
+
+        self._settings = {
+            "language_codes": [
+                self.language_to_service_language(lang) for lang in params.language_list
+            ],
+            "model": params.model,
+            "use_separate_recognition_per_channel": params.use_separate_recognition_per_channel,
+            "enable_automatic_punctuation": params.enable_automatic_punctuation,
+            "enable_spoken_punctuation": params.enable_spoken_punctuation,
+            "enable_spoken_emojis": params.enable_spoken_emojis,
+            "profanity_filter": params.profanity_filter,
+            "enable_word_time_offsets": params.enable_word_time_offsets,
+            "enable_word_confidence": params.enable_word_confidence,
+            "enable_interim_results": params.enable_interim_results,
+            "enable_voice_activity_events": params.enable_voice_activity_events,
+        }
+
+    def language_to_service_language(self, language: Language | List[Language]) -> str | List[str]:
+        """Convert Language enum(s) to Google STT language code(s).
+
+        Args:
+            language: Single Language enum or list of Language enums.
+
+        Returns:
+            str | List[str]: Google STT language code(s).
+        """
+        if isinstance(language, list):
+            return [language_to_google_stt_language(lang) or "en-US" for lang in language]
+        return language_to_google_stt_language(language) or "en-US"
+
+    async def _reconnect_if_needed(self):
+        """Reconnect the stream if it's currently active."""
+        if self._streaming_task:
+            logger.debug("Reconnecting stream due to configuration changes")
+            await self._disconnect()
+            await self._connect()
+
+    async def set_languages(self, languages: List[Language]):
+        """Update the service's recognition languages.
+
+        Args:
+            languages: List of languages for recognition. First language is primary.
+        """
+        logger.debug(f"Switching STT languages to: {languages}")
+        self._settings["language_codes"] = [
+            self.language_to_service_language(lang) for lang in languages
+        ]
+        # Recreate stream with new languages
+        await self._reconnect_if_needed()
+
+    async def set_model(self, model: str):
+        """Update the service's recognition model."""
+        logger.debug(f"Switching STT model to: {model}")
+        await super().set_model(model)
+        self._settings["model"] = model
+        # Recreate stream with new model
+        await self._reconnect_if_needed()
+
+    async def start(self, frame: StartFrame):
+        await super().start(frame)
+        await self._connect()
+
+    async def stop(self, frame: EndFrame):
+        await super().stop(frame)
+        await self._disconnect()
+
+    async def cancel(self, frame: CancelFrame):
+        await super().cancel(frame)
+        await self._disconnect()
+
+    async def update_options(
+        self,
+        *,
+        languages: Optional[List[Language]] = None,
+        model: Optional[str] = None,
+        enable_automatic_punctuation: Optional[bool] = None,
+        enable_spoken_punctuation: Optional[bool] = None,
+        enable_spoken_emojis: Optional[bool] = None,
+        profanity_filter: Optional[bool] = None,
+        enable_word_time_offsets: Optional[bool] = None,
+        enable_word_confidence: Optional[bool] = None,
+        enable_interim_results: Optional[bool] = None,
+        enable_voice_activity_events: Optional[bool] = None,
+        location: Optional[str] = None,
+    ) -> None:
+        """Update service options dynamically.
+
+        Args:
+            languages: New list of recongition languages.
+            model: New recognition model.
+            enable_automatic_punctuation: Enable/disable automatic punctuation.
+            enable_spoken_punctuation: Enable/disable spoken punctuation.
+            enable_spoken_emojis: Enable/disable spoken emojis.
+            profanity_filter: Enable/disable profanity filter.
+            enable_word_time_offsets: Enable/disable word timing info.
+            enable_word_confidence: Enable/disable word confidence scores.
+            enable_interim_results: Enable/disable interim results.
+            enable_voice_activity_events: Enable/disable voice activity detection.
+            location: New Google Cloud location.
+
+        Note:
+            Changes that affect the streaming configuration will cause
+            the stream to be reconnected.
+        """
+        # Update settings with new values
+        if languages is not None:
+            logger.debug(f"Updating language to: {languages}")
+            self._settings["language_codes"] = [
+                self.language_to_service_language(lang) for lang in languages
+            ]
+
+        if model is not None:
+            logger.debug(f"Updating model to: {model}")
+            self._settings["model"] = model
+
+        if enable_automatic_punctuation is not None:
+            logger.debug(f"Updating automatic punctuation to: {enable_automatic_punctuation}")
+            self._settings["enable_automatic_punctuation"] = enable_automatic_punctuation
+
+        if enable_spoken_punctuation is not None:
+            logger.debug(f"Updating spoken punctuation to: {enable_spoken_punctuation}")
+            self._settings["enable_spoken_punctuation"] = enable_spoken_punctuation
+
+        if enable_spoken_emojis is not None:
+            logger.debug(f"Updating spoken emojis to: {enable_spoken_emojis}")
+            self._settings["enable_spoken_emojis"] = enable_spoken_emojis
+
+        if profanity_filter is not None:
+            logger.debug(f"Updating profanity filter to: {profanity_filter}")
+            self._settings["profanity_filter"] = profanity_filter
+
+        if enable_word_time_offsets is not None:
+            logger.debug(f"Updating word time offsets to: {enable_word_time_offsets}")
+            self._settings["enable_word_time_offsets"] = enable_word_time_offsets
+
+        if enable_word_confidence is not None:
+            logger.debug(f"Updating word confidence to: {enable_word_confidence}")
+            self._settings["enable_word_confidence"] = enable_word_confidence
+
+        if enable_interim_results is not None:
+            logger.debug(f"Updating interim results to: {enable_interim_results}")
+            self._settings["enable_interim_results"] = enable_interim_results
+
+        if enable_voice_activity_events is not None:
+            logger.debug(f"Updating voice activity events to: {enable_voice_activity_events}")
+            self._settings["enable_voice_activity_events"] = enable_voice_activity_events
+
+        if location is not None:
+            logger.debug(f"Updating location to: {location}")
+            self._location = location
+
+        # Reconnect the stream for updates
+        await self._reconnect_if_needed()
+
+    async def _connect(self):
+        """Initialize streaming recognition config and stream."""
+        logger.debug("Connecting to Google Speech-to-Text")
+
+        # Set stream start time
+        self._stream_start_time = int(time.time() * 1000)
+        self._new_stream = True
+
+        self._config = cloud_speech.StreamingRecognitionConfig(
+            config=cloud_speech.RecognitionConfig(
+                explicit_decoding_config=cloud_speech.ExplicitDecodingConfig(
+                    encoding=cloud_speech.ExplicitDecodingConfig.AudioEncoding.LINEAR16,
+                    sample_rate_hertz=self.sample_rate,
+                    audio_channel_count=1,
+                ),
+                language_codes=self._settings["language_codes"],
+                model=self._settings["model"],
+                features=cloud_speech.RecognitionFeatures(
+                    enable_automatic_punctuation=self._settings["enable_automatic_punctuation"],
+                    enable_spoken_punctuation=self._settings["enable_spoken_punctuation"],
+                    enable_spoken_emojis=self._settings["enable_spoken_emojis"],
+                    profanity_filter=self._settings["profanity_filter"],
+                    enable_word_time_offsets=self._settings["enable_word_time_offsets"],
+                    enable_word_confidence=self._settings["enable_word_confidence"],
+                ),
+            ),
+            streaming_features=cloud_speech.StreamingRecognitionFeatures(
+                enable_voice_activity_events=self._settings["enable_voice_activity_events"],
+                interim_results=self._settings["enable_interim_results"],
+            ),
+        )
+
+        self._streaming_task = self.create_task(self._stream_audio())
+
+    async def _disconnect(self):
+        """Clean up streaming recognition resources."""
+        if self._streaming_task:
+            logger.debug("Disconnecting from Google Speech-to-Text")
+            # Send sentinel value to stop request generator
+            await self._request_queue.put(None)
+            await self.cancel_task(self._streaming_task)
+            self._streaming_task = None
+            # Clear any remaining items in the queue
+            while not self._request_queue.empty():
+                try:
+                    self._request_queue.get_nowait()
+                    self._request_queue.task_done()
+                except asyncio.QueueEmpty:
+                    break
+
+    async def _request_generator(self):
+        """Generates requests for the streaming recognize method."""
+        recognizer_path = f"projects/{self._project_id}/locations/{self._location}/recognizers/_"
+        logger.trace(f"Using recognizer path: {recognizer_path}")
+
+        try:
+            # Send initial config
+            yield cloud_speech.StreamingRecognizeRequest(
+                recognizer=recognizer_path,
+                streaming_config=self._config,
+            )
+
+            while True:
+                try:
+                    audio_data = await self._request_queue.get()
+                    if audio_data is None:  # Sentinel value to stop
+                        break
+
+                    # Check streaming limit
+                    if (int(time.time() * 1000) - self._stream_start_time) > self.STREAMING_LIMIT:
+                        logger.debug("Streaming limit reached, initiating graceful reconnection")
+                        # Instead of immediate reconnection, we'll break and let the stream close naturally
+                        self._last_audio_input = self._audio_input
+                        self._audio_input = []
+                        self._restart_counter += 1
+                        # Put the current audio chunk back in the queue
+                        await self._request_queue.put(audio_data)
+                        break
+
+                    self._audio_input.append(audio_data)
+                    yield cloud_speech.StreamingRecognizeRequest(audio=audio_data)
+
+                except asyncio.CancelledError:
+                    break
+                finally:
+                    self._request_queue.task_done()
+
+        except Exception as e:
+            logger.error(f"Error in request generator: {e}")
+            raise
+
+    async def _stream_audio(self):
+        """Handle bi-directional streaming with Google STT."""
+        try:
+            while True:
+                try:
+                    # Start bi-directional streaming
+                    streaming_recognize = await self._client.streaming_recognize(
+                        requests=self._request_generator()
+                    )
+
+                    # Process responses
+                    await self._process_responses(streaming_recognize)
+
+                    # If we're here, check if we need to reconnect
+                    if (int(time.time() * 1000) - self._stream_start_time) > self.STREAMING_LIMIT:
+                        logger.debug("Reconnecting stream after timeout")
+                        # Reset stream start time
+                        self._stream_start_time = int(time.time() * 1000)
+                        continue
+                    else:
+                        # Normal stream end
+                        break
+
+                except Exception as e:
+                    logger.error(f"Stream error, attempting to reconnect: {e}")
+                    await asyncio.sleep(1)  # Brief delay before reconnecting
+                    self._stream_start_time = int(time.time() * 1000)
+                    continue
+
+        except Exception as e:
+            logger.error(f"Error in streaming task: {e}")
+            await self.push_frame(ErrorFrame(str(e)))
+
+    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
+        """Process an audio chunk for STT transcription."""
+        if self._streaming_task:
+            # Queue the audio data
+            await self._request_queue.put(audio)
+        yield None
+
+    async def _process_responses(self, streaming_recognize):
+        """Process streaming recognition responses."""
+        try:
+            async for response in streaming_recognize:
+                # Check streaming limit
+                if (int(time.time() * 1000) - self._stream_start_time) > self.STREAMING_LIMIT:
+                    logger.debug("Stream timeout reached in response processing")
+                    break
+
+                if not response.results:
+                    continue
+
+                for result in response.results:
+                    if not result.alternatives:
+                        continue
+
+                    transcript = result.alternatives[0].transcript
+                    if not transcript:
+                        continue
+
+                    primary_language = self._settings["language_codes"][0]
+
+                    if result.is_final:
+                        self._last_transcript_was_final = True
+                        await self.push_frame(
+                            TranscriptionFrame(transcript, "", time_now_iso8601(), primary_language)
+                        )
+                    else:
+                        self._last_transcript_was_final = False
+                        await self.push_frame(
+                            InterimTranscriptionFrame(
+                                transcript, "", time_now_iso8601(), primary_language
+                            )
+                        )
+
+        except Exception as e:
+            logger.error(f"Error processing Google STT responses: {e}")
--- a/src/pipecat/transcriptions/language.py
+++ b/src/pipecat/transcriptions/language.py
@@ -101,6 +101,7 @@ class Language(StrEnum):
    EN_AU = "en-AU"
    EN_CA = "en-CA"
    EN_GB = "en-GB"
+    EN_GH = "en-GH"
    EN_HK = "en-HK"
    EN_IE = "en-IE"
    EN_IN = "en-IN"
@@ -208,6 +209,7 @@ class Language(StrEnum):
    # Italian
    IT = "it"
    IT_IT = "it-IT"
+    IT_CH = "it-CH"

    # Inuktitut
    IU_CANS = "iu-Cans"