Add Soniox STT service

examples/foundational/13f-soniox-transcription.py

@@ -0,0 +1,77 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+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.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.soniox.config import SonioxInputParams
+from pipecat.services.soniox.stt import SonioxSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
+
+load_dotenv(override=True)
+
+
+class TranscriptionLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
+    logger.info(f"Starting bot")
+
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(audio_in_enabled=True),
+    )
+
+    stt = SonioxSTTService(
+        api_key=os.getenv("SONIOX_API_KEY"),
+        params=SonioxInputParams(
+            # Add language hints to improve transcription accuracy. Variants are ignored.
+            # For example "en-GB" will be treated same as "en".
+            # List of supported languages: https://soniox.com/docs/speech-to-text/core-concepts/supported-languages
+            language_hints=[Language.EN, Language.ES, Language.JA, Language.ZH],
+        ),
+    )
+
+    tl = TranscriptionLogger()
+
+    pipeline = Pipeline([transport.input(), stt, tl])
+
+    task = PipelineTask(pipeline)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()