feat(qwen-audio): add Alibaba Cloud Qwen-Audio Realtime service integration

- Introduced Qwen-Audio Realtime service for speech-to-speech processing in Pipecat.
- Updated interface catalog to include Qwen-Audio Realtime capabilities.
- Enhanced model resource testing to support new service.
- Added configuration options for audio sample rates and turn detection modes.
- Updated documentation to reflect integration details and usage instructions.

backend/services/pipecat/pipeline.py

@@ -26,6 +26,7 @@ from services.pipecat.service_factory import (
     create_realtime_service,
     create_stt,
     create_tts,
+    realtime_audio_sample_rates,
 )
 from db.session import SessionLocal
 from services.knowledge import search as search_knowledge
@@ -692,6 +693,7 @@ async def run_realtime_pipeline(
         cfg,
         instructions=brain.system_prompt(cfg),
     )
+    input_sample_rate, output_sample_rate = realtime_audio_sample_rates(cfg)
     text_input = RealtimeTextInputProcessor()
     dynamic_variables = RealtimeDynamicVariableProcessor(brain, cfg, realtime)
     greeting = await brain.greeting(cfg)
@@ -717,12 +719,8 @@ async def run_realtime_pipeline(
         pipeline,
         params=PipelineParams(
             enable_metrics=False,
-            audio_in_sample_rate=int(
-                cfg.realtime_values.get("inputSampleRate") or 24000
-            ),
-            audio_out_sample_rate=int(
-                cfg.realtime_values.get("outputSampleRate") or 24000
-            ),
+            audio_in_sample_rate=input_sample_rate,
+            audio_out_sample_rate=output_sample_rate,
         ),
         enable_rtvi=False,
     )