sync

configs/config.yaml

@@ -1,5 +1,5 @@
 # =================== Lord Of Large Language Multimodal Systems Configuration file =========================== 
-version: 96
+version: 98
 binding_name: null
 model_name: null
 model_variant: null
@@ -80,10 +80,30 @@ auto_show_browser: true
 # copy to clipboard 
 copy_to_clipboard_add_all_details: false
 
+# -------------------- Services global configurations --------------------------
+# Select the active test to speach, text to image and speach to text services
+active_tts_service: "None" # xtts (offline), openai_tts (API key required)
+active_tti_service: "None" # autosd (offline), dall-e (online)
+active_stt_service: "None" # whisper (offline), asr (offline or online), openai_whiosper (API key required)
+
+# -------------------- Services --------------------------
+
+# ***************** STT *****************
 # STT service 
 asr_enable: false
 asr_base_url: http://localhost:9000
 
+# openai_whisper configuration
+openai_whisper_key: ""
+openai_whisper_model: "whisper-1"
+
+
+# whisper configuration
+whisper_activate: false
+whisper_model: base
+
+
+# ***************** TTS *****************
 # Voice service
 xtts_enable: false
 xtts_base_url: http://localhost:8020
@@ -101,6 +121,13 @@ xtts_top_p: 0.85
 xtts_speed: 1
 xtts_enable_text_splitting: true
 
+# openai_whisper configuration
+openai_tts_key: ""
+openai_tts_model: "tts-1"
+openai_tts_voice: "alloy"
+
+# ***************** TTI *****************
+
 # Image generation service
 enable_sd_service: false
 sd_base_url: http://localhost:7860
@@ -109,6 +136,8 @@ sd_base_url: http://localhost:7860
 dall_e_key: ""
 dall_e_generation_engine: "dall-e-3"
 
+# Midjourney service key
+midjourney_key: ""
 
 # Image generation service comfyui
 enable_comfyui_service: false
@@ -118,6 +147,8 @@ comfyui_base_url: http://127.0.0.1:8188/
 enable_motion_ctrl_service: false
 motion_ctrl_base_url: http://localhost:7861
 
+# ***************** TTT *****************
+
 # ollama service
 enable_ollama_service: false
 ollama_base_url: http://localhost:11434
@@ -202,6 +233,3 @@ show_code_of_conduct: true
 activate_audio_infos: true
 
 
-# whisper configuration
-whisper_activate: false
-whisper_model: base

lollms_core

@@ -1 +1 @@
-Subproject commit 42ebabfe0d8c70f6ec13d5585e52212c4aa15cb8
+Subproject commit 397d21a3bef1d555ec18eff7308859ff40e78519

lollms_webui.py

@@ -402,6 +402,8 @@ class LOLLMSWebUI(LOLLMSElfServer):
 
 
 
+
+
     def rebuild_personalities(self, reload_all=False):
         if reload_all:
             self.mounted_personalities=[]
@@ -1199,7 +1201,7 @@ class LOLLMSWebUI(LOLLMSElfServer):
                                     client_id=client_id,
                                     callback=partial(self.process_chunk,client_id = client_id)
                                 )
-                    if self.config.xtts_enable and self.config.auto_read and len(self.personality.audio_samples)>0:
+                    if self.tts and self.config.auto_read and len(self.personality.audio_samples)>0:
                         try:
                             self.process_chunk("Generating voice output",MSG_TYPE.MSG_TYPE_STEP_START,client_id=client_id)
                             from lollms.services.xtts.lollms_xtts import LollmsXTTS
@@ -1209,22 +1211,13 @@ class LOLLMSWebUI(LOLLMSElfServer):
                             else:
                                 voices_folder = Path(__file__).parent.parent.parent/"services/xtts/voices"
 
-                            if self.tts is None:
-                                self.tts = LollmsXTTS(
-                                                        self, 
-                                                        voices_folder=voices_folder,
-                                                        voice_samples_path=Path(__file__).parent.parent/"voices", 
-                                                        xtts_base_url= self.config.xtts_base_url,
-                                                        use_deep_speed=self.config.xtts_use_deepspeed,
-                                                        use_streaming_mode=self.config.xtts_use_streaming_mode                                                        
-                                                    )
-                            if self.tts.ready:
+                            if self.xtts.ready:
                                 language = convert_language_name(self.personality.language)
-                                self.tts.set_speaker_folder(Path(self.personality.audio_samples[0]).parent)
+                                self.xtts.set_speaker_folder(Path(self.personality.audio_samples[0]).parent)
                                 fn = self.personality.name.lower().replace(' ',"_").replace('.','')    
                                 fn = f"{fn}_{message_id}.wav"
                                 url = f"audio/{fn}"
-                                self.tts.tts_to_file(client.generated_text, Path(self.personality.audio_samples[0]).name, f"{fn}", language=language)
+                                self.xtts.tts_to_file(client.generated_text, Path(self.personality.audio_samples[0]).name, f"{fn}", language=language)
                                 fl = f"\n".join([
                                 f"<audio controls>",
                                 f'    <source src="{url}" type="audio/wav">',

web/dist/index.html

@@ -6,8 +6,8 @@
     
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>LoLLMS WebUI - Welcome</title>
-    <script type="module" crossorigin src="/assets/index-ce134d76.js"></script>
-    <link rel="stylesheet" href="/assets/index-d51e4b15.css">
+    <script type="module" crossorigin src="/assets/index-0266685d.js"></script>
+    <link rel="stylesheet" href="/assets/index-0a0ae0b8.css">
   </head>
   <body>
     <div id="app"></div>

zoos/personalities_zoo

@@ -1 +1 @@
-Subproject commit e0bcb7028277a1936f7875633dc507cf0cbb92dc
+Subproject commit 029f45f3d876a6e95107087044cf5bac16ff8880