Add support for Xfyun ASR and TTS services in the backend

- Introduce new Xfyun ASR and TTS services, enabling integration with iFlytek's voice recognition and synthesis capabilities.
- Update AssistantConfig model to include interface types for STT and TTS.
- Enhance credential testing to validate Xfyun credentials.
- Modify service factory to create Xfyun services based on configuration.
- Update README with new configuration details for Xfyun integration.
- Add new frontend components for visualizing audio streams and managing user interactions.

backend/services/pipecat/service_factory.py

@@ -13,6 +13,20 @@ from pipecat.services.openai.stt import OpenAISTTService
 from pipecat.services.openai.tts import VALID_VOICES, OpenAITTSService
 from pipecat.transcriptions.language import Language
 
+from services.pipecat.xfyun_asr import DEFAULT_XFYUN_ASR_URL, XfyunASRService
+from services.pipecat.xfyun_config import (
+    is_super_tts,
+    parse_xfyun_credential,
+    websocket_url,
+    xfyun_language,
+    xfyun_speed,
+)
+from services.pipecat.xfyun_super_tts import (
+    DEFAULT_XFYUN_SUPER_TTS_URL,
+    XfyunSuperTTSService,
+)
+from services.pipecat.xfyun_tts import DEFAULT_XFYUN_TTS_URL, XfyunTTSService
+
 
 def _language(value: str) -> Language | None:
     if not value:
@@ -29,11 +43,24 @@ def create_stt(cfg: AssistantConfig):
 
     连接信息优先用 cfg(由 config_resolver 从 DB 注入),为空回退 .env 默认。
     """
+    if cfg.stt_interface_type == "xfyun":
+        credential = parse_xfyun_credential(cfg.stt_api_key)
+        return XfyunASRService(
+            app_id=credential.app_id,
+            api_key=credential.api_key,
+            api_secret=credential.api_secret,
+            url=websocket_url(cfg.stt_base_url, DEFAULT_XFYUN_ASR_URL),
+            language=xfyun_language(cfg.stt_language),
+            sample_rate=16000,
+        )
+
     return OpenAISTTService(
         api_key=cfg.stt_api_key or config.STT_API_KEY,
         base_url=cfg.stt_base_url or config.STT_BASE_URL,
-        model=cfg.asr or config.STT_MODEL,
-        language=_language(cfg.stt_language),
+        settings=OpenAISTTService.Settings(
+            model=cfg.asr or config.STT_MODEL,
+            language=_language(cfg.stt_language),
+        ),
     )
 
 
@@ -42,13 +69,39 @@ def create_llm(cfg: AssistantConfig):
     return OpenAILLMService(
         api_key=cfg.llm_api_key or config.LLM_API_KEY,
         base_url=cfg.llm_base_url or config.LLM_BASE_URL,
-        model=cfg.model or config.LLM_MODEL,
+        settings=OpenAILLMService.Settings(model=cfg.model or config.LLM_MODEL),
     )
 
 
 def create_tts(cfg: AssistantConfig):
     """CosyVoice 等,走 OpenAI 兼容的 /v1/audio/speech。"""
     voice = cfg.voice or config.TTS_VOICE
+    if cfg.tts_interface_type == "xfyun":
+        credential = parse_xfyun_credential(cfg.tts_api_key)
+        speed = xfyun_speed(cfg.tts_speed)
+        if is_super_tts(cfg.tts_model, cfg.tts_base_url):
+            return XfyunSuperTTSService(
+                app_id=credential.app_id,
+                api_key=credential.api_key,
+                api_secret=credential.api_secret,
+                voice=voice,
+                url=websocket_url(cfg.tts_base_url, DEFAULT_XFYUN_SUPER_TTS_URL),
+                sample_rate=16000,
+                source_sample_rate=24000,
+                speed=speed,
+            )
+        return XfyunTTSService(
+            app_id=credential.app_id,
+            api_key=credential.api_key,
+            api_secret=credential.api_secret,
+            voice=voice,
+            url=websocket_url(cfg.tts_base_url, DEFAULT_XFYUN_TTS_URL),
+            sample_rate=16000,
+            source_sample_rate=16000,
+            speed=speed,
+            push_stop_frames=True,
+        )
+
     # Pipecat 默认只接受 OpenAI 官方音色。OpenAI 兼容服务常使用自定义 voice id,
     # 注册为原样映射后仍由 OpenAI SDK 按字符串透传给供应商。
     VALID_VOICES.setdefault(voice, voice)
@@ -65,9 +118,9 @@ def create_tts(cfg: AssistantConfig):
 
 def create_services(cfg: AssistantConfig):
     logger.info(
-        f"创建服务: stt={cfg.asr or config.STT_MODEL} "
+        f"创建服务: stt={cfg.stt_interface_type}/{cfg.asr or config.STT_MODEL} "
         f"llm={cfg.model or config.LLM_MODEL} "
-        f"tts={cfg.tts_model or config.TTS_MODEL} "
+        f"tts={cfg.tts_interface_type}/{cfg.tts_model or config.TTS_MODEL} "
         f"voice={cfg.voice or config.TTS_VOICE}"
     )
     return create_stt(cfg), create_llm(cfg), create_tts(cfg)