add support for TTS model (#2095)

### What problem does this PR solve?

add support for TTS model
#1853

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

rag/llm/__init__.py

@@ -18,6 +18,7 @@ from .chat_model import *
 from .cv_model import *
 from .rerank_model import *
 from .sequence2txt_model import *
+from .tts_model import * 
 
 EmbeddingModel = {
     "Ollama": OllamaEmbed,
@@ -129,3 +130,7 @@ Seq2txtModel = {
     "Azure-OpenAI": AzureSeq2txt,
     "Xinference": XinferenceSeq2txt
 }
+
+TTSModel = {
+    "Fish Audio": FishAudioTTS
+}