Add changelog for #4340

changelog/4340.added.md

@@ -0,0 +1 @@
+- Added `XAISTTService` for real-time speech-to-text using xAI's voice STT WebSocket API (`wss://api.x.ai/v1/stt`). Streams raw audio (PCM, µ-law, or A-law) and emits interim and final transcription frames driven by the server's `is_final` / `speech_final` flags. Settings expose `interim_results`, `endpointing`, `language`, `multichannel`, `channels`, and `diarize`. Requires the `xai` optional extra (`pip install "pipecat-ai[xai]"`).

examples/transcription/transcription-xai.py

@@ -9,12 +9,10 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -58,9 +56,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
-    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
     task = PipelineTask(
         pipeline,

src/pipecat/services/xai/stt.py

@@ -321,7 +321,6 @@ class XAISTTService(WebsocketSTTService):
     async def _handle_message(self, message: dict[str, Any]):
         """Branch on xAI STT event type."""
         msg_type = message.get("type")
-        print(f"xAI STT message: {message}")
 
         if msg_type == "transcript.created":
             self._session_ready.set()