Merge pull request #2375 from fabrice404/gladia-region-selection

Gladia region selection

CHANGELOG.md

@@ -46,6 +46,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added Chinese, Japanese, Korean word timestamp support to
   `CartesiaTTSService`.
 
+- Added `region` parameter to `GladiaSTTService`. Accepted values: eu-west (default), us-west.
+
 ### Changed
 
 - System frames are now queued. Before, system frames could be generated from

env.example

@@ -44,6 +44,7 @@ FIREWORKS_API_KEY=...
 
 # Gladia
 GLADIA_API_KEY=...
+GLADIA_REGION=...
 
 # Google
 GOOGLE_API_KEY=...
@@ -135,4 +136,4 @@ SAMBANOVA_API_KEY=...
 SENTRY_DSN=...
 
 # Heygen
-HEYGEN_API_KEY=...
+HEYGEN_API_KEY=...

examples/foundational/07j-interruptible-gladia.py

@@ -55,6 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY", ""),
+        region=os.getenv("GLADIA_REGION"),
         params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],

examples/foundational/13c-gladia-transcription.py

@@ -47,6 +47,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
+        region=os.getenv("GLADIA_REGION"),
         # live_options=LiveOptions(language=Language.FR),
     )
 

examples/foundational/13c-gladia-translation.py

@@ -56,6 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
+        region=os.getenv("GLADIA_REGION"),
         params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],  # Input in English

src/pipecat/services/gladia/stt.py

@@ -14,7 +14,8 @@ import asyncio
 import base64
 import json
 import warnings
-from typing import Any, AsyncGenerator, Dict, Optional
+from typing import Any, AsyncGenerator, Dict, Literal, Optional
+from urllib.parse import urlencode
 
 import aiohttp
 from loguru import logger
@@ -203,6 +204,7 @@ class GladiaSTTService(STTService):
         self,
         *,
         api_key: str,
+        region: Optional[Literal["us-west", "eu-west"]] = "eu-west",
         url: str = "https://api.gladia.io/v2/live",
         confidence: float = 0.5,
         sample_rate: Optional[int] = None,
@@ -217,6 +219,7 @@ class GladiaSTTService(STTService):
 
         Args:
             api_key: Gladia API key for authentication.
+            region: Region used to process audio. eu-west or us-west. Defaults to eu-west.
             url: Gladia API URL. Defaults to "https://api.gladia.io/v2/live".
             confidence: Minimum confidence threshold for transcriptions (0.0-1.0).
             sample_rate: Audio sample rate in Hz. If None, uses service default.
@@ -241,6 +244,7 @@ class GladiaSTTService(STTService):
             )
 
         self._api_key = api_key
+        self._region = region
         self._url = url
         self.set_model_name(model)
         self._confidence = confidence
@@ -337,6 +341,13 @@ class GladiaSTTService(STTService):
 
         return settings
 
+    def _get_endpoint_url(self) -> str:
+        query_params = dict()
+        query_params["region"] = self._region or "eu-west"
+        query = urlencode(query_params)
+
+        return f"{self._url}?{query}"
+
     async def start(self, frame: StartFrame):
         """Start the Gladia STT websocket connection.
 
@@ -485,11 +496,13 @@ class GladiaSTTService(STTService):
     async def _setup_gladia(self, settings: Dict[str, Any]):
         async with aiohttp.ClientSession() as session:
             async with session.post(
-                self._url,
+                self._get_endpoint_url(),
                 headers={"X-Gladia-Key": self._api_key, "Content-Type": "application/json"},
                 json=settings,
             ) as response:
                 if response.ok:
+                    response_text = await response.json()
+                    logger.error(f"Gladia response: {response_text}")
                     return await response.json()
                 else:
                     error_text = await response.text()