Add max_endpoint_delay_ms and clean up Sonoix STT settings (#4521)

examples/update-settings/stt/stt-soniox.py

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.soniox.stt import SonioxSTTService
+from pipecat.services.soniox.tts import SonioxTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -53,12 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = SonioxSTTService(api_key=os.environ["SONIOX_API_KEY"])
 
-    tts = CartesiaTTSService(
+    tts = SonioxTTSService(api_key=os.environ["SONIOX_API_KEY"])
-        api_key=os.environ["CARTESIA_API_KEY"],
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
-    )
 
     llm = OpenAILLMService(
         api_key=os.environ["OPENAI_API_KEY"],
@@ -103,9 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         await task.queue_frames([LLMRunFrame()])
 
         await asyncio.sleep(10)
-        logger.info("Updating Soniox STT settings: language=es")
+        logger.info("Updating Soniox STT settings: language_hints=[es]")
         await task.queue_frame(
-            STTUpdateSettingsFrame(delta=SonioxSTTService.Settings(language=Language.ES))
+            STTUpdateSettingsFrame(delta=SonioxSTTService.Settings(language_hints=[Language.ES]))
         )
 
     @transport.event_handler("on_client_disconnected")

src/pipecat/services/soniox/stt.py

@@ -155,7 +155,6 @@ def language_to_soniox_language(language: Language) -> str:
         Language.ID: "id",
         Language.IT: "it",
         Language.JA: "ja",
-        Language.KA: "ka",
         Language.KK: "kk",
         Language.KN: "kn",
         Language.KO: "ko",
@@ -232,6 +231,7 @@ class SonioxSTTSettings(STTSettings):
             context_version 2.
         enable_speaker_diarization: Whether to enable speaker diarization.
         enable_language_identification: Whether to enable language identification.
+        max_endpoint_delay_ms: Max ms before endpoint detection finalizes the turn (500-3000).
         client_reference_id: Client reference ID to use for transcription.
     """
 
@@ -242,6 +242,7 @@ class SonioxSTTSettings(STTSettings):
     enable_language_identification: bool | None | _NotGiven = field(
         default_factory=lambda: NOT_GIVEN
     )
+    max_endpoint_delay_ms: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
     client_reference_id: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
 
 
@@ -309,6 +310,7 @@ class SonioxSTTService(WebsocketSTTService):
             context=None,
             enable_speaker_diarization=False,
             enable_language_identification=False,
+            max_endpoint_delay_ms=None,
             client_reference_id=None,
         )
 
@@ -390,8 +392,7 @@ class SonioxSTTService(WebsocketSTTService):
         changed = await super()._update_settings(delta)
 
         if changed:
-            await self._disconnect()
+            await self._request_reconnect()
-            await self._connect()
 
         return changed
 
@@ -522,6 +523,7 @@ class SonioxSTTService(WebsocketSTTService):
                 "audio_format": self._audio_format,
                 "num_channels": self._num_channels,
                 "enable_endpoint_detection": enable_endpoint_detection,
+                "max_endpoint_delay_ms": s.max_endpoint_delay_ms,
                 "sample_rate": self.sample_rate,
                 "language_hints": _prepare_language_hints(assert_given(s.language_hints)),
                 "language_hints_strict": s.language_hints_strict,