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/db/seed_model_resources.sql

@@ -50,6 +50,9 @@ VALUES
    '{"apiKey":"replace-me"}', FALSE, TRUE, FALSE),
   ('model_016', 'OpenCode 服务', 'Agent', 'opencode',
    '{"apiUrl":"http://localhost:4096"}',
+   '{"apiKey":"replace-me"}', FALSE, TRUE, FALSE),
+  ('model_017', 'Qwen-Audio 3.0 Realtime', 'Realtime', 'qwen-audio-realtime',
+   '{"modelId":"qwen-audio-3.0-realtime-flash","apiUrl":"wss://replace-with-workspace-id.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime","voice":"longanqian","turnDetection":"server_vad","vadThreshold":0.5,"silenceDurationMs":800,"maxHistoryTurns":20}',
    '{"apiKey":"replace-me"}', FALSE, TRUE, FALSE)
 -- Seed defaults must never overwrite resources configured through the UI.
 ON CONFLICT (id) DO NOTHING;