Enhance credential management and testing functionality

- Introduce new fields for voice, speed, and language in the AssistantConfig and ProviderCredential models to support TTS and ASR configurations.
- Update the database schema and seeding script to accommodate the new fields, ensuring backward compatibility.
- Implement credential testing endpoints and logic to validate OpenAI-compatible credentials, enhancing user experience and reliability.
- Modify frontend components to include new fields in the credential forms and improve connection testing feedback.
- Refactor related services and API interactions to support the new credential testing feature.

backend/services/config_resolver.py

@@ -58,7 +58,9 @@ async def resolve_runtime_config(
         # 模型/音色:凭证的模型ID优先
         model=(llm.model_id if llm else ""),
         asr=(stt.model_id if stt else ""),
-        voice="",  # 音色无独立列,留空 → service_factory 回退 .env TTS_VOICE
+        voice=(tts.voice if tts else ""),
+        stt_language=(stt.language if stt else ""),
+        tts_speed=(tts.speed if tts else 1.0),
         realtimeModel=(realtime.model_id if realtime else ""),
         # 运行时连接信息(真 key + url):凭证优先,否则 .env 兜底
         llm_api_key=(llm.api_key if llm else config.LLM_API_KEY),