Version 3.0.12

Fix F5-TTS model switching and improve initialization messages

- Fixed F5-TTS model cache not reloading when changing model names
- Added F5-TTS availability checking to initialization messages
- Improved F5-TTS model loading to only check matching local folders
- Removed redundant SRT success messages (only show on actual issues)
- Enhanced error handling for missing F5-TTS dependencies

Author: diodiogod

CHANGELOG.md

@@ -5,6 +5,22 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.0.12] - 2025-07-16
+
+### Added
+
+- Added F5-TTS availability checking to initialization messages
+
+### Fixed
+
+- Fix F5-TTS model switching and improve initialization messages
+- Fixed F5-TTS model cache not reloading when changing model names
+- Removed redundant SRT success messages (only show on actual issues)
+- Enhanced error handling for missing F5-TTS dependencies
+
+### Changed
+
+- Improved F5-TTS model loading to only check matching local folders
 ## [3.0.11] - 2025-07-16
 
 ### Removed

README.md

@@ -6,20 +6,26 @@
 [![Forks][forks-shield]][forks-url]
 [![Dynamic TOML Badge][version-shield]][version-url]
 
-# ComfyUI ChatterBox SRT Voice (diogod) v3.0.11
+# ComfyUI ChatterBox SRT Voice (diogod) v3.0.12
 
 *This is a refactored node, originally created by [ShmuelRonen](https://github.com/ShmuelRonen/ComfyUI_ChatterBox_Voice).*
 
+<div align="center">
+  <img src="images/AllNodesShowcase.png" alt="ComfyUI ChatterBox Voice Nodes Showcase" />
+</div>
+
 An unofficial ComfyUI custom node integration for High-quality Text-to-Speech and Voice Conversion nodes for ComfyUI using ResembleAI's ChatterboxTTS with unlimited text length and with a node specially made for dealing with SRT timings.
 
-## 🆕 What's New in v3.0+
+## 🆕 What's New in my Project?
 
 ### SRT Timing and TTS Node
-![SRT Node Screenshot](images/srt.png)
+
+<img title="" src="images/srt.png" alt="SRT Node Screenshot" width="500" data-align="center">
 
 The **"ChatterBox SRT Voice TTS"** node allows TTS generation by processing SRT content (SubRip Subtitle) files, ensuring precise timing and synchronization with your audio.
 
 **Key SRT Features:**
+
 * **SRT style Processing**: Uses SRT style to generate TTS, aligning audio with subtitle timings
 * **`smart_natural` Timing Mode**: Intelligent shifting logic that prevents overlaps and ensures natural speech flow
 * **`Adjusted_SRT` Output**: Provides actual timings for generated audio for accurate post-processing
@@ -32,16 +38,25 @@ For comprehensive technical information, refer to the [SRT_IMPLEMENTATION.md](do
 
 </details>
 
-### F5-TTS Integration and Audio Analyzer
-![F5-TTS and Audio Analyzer](images/f5_tts_audio_analyzer_screenshot.png)
-> 📸 **Placeholder image** - Screenshot coming soon
+### 🆕 F5-TTS Integration and 🆕 Audio Analyzer
+
+<img title="" src="images/waveanalgif.gif" alt="Audio Wave gif" width="500" data-align="center">
 
 * **F5-TTS Voice Synthesis**: High-quality voice cloning with reference audio + text
 * **Audio Wave Analyzer**: Interactive waveform visualization for precise timing extraction
 * **Multi-language Support**: English, German, Spanish, French, Japanese models
-* **Speech Editing Workflows**: Advanced F5-TTS editing capabilities
+* **Speech Editing Workflows**: Advanced F5-TTS editing capabilities 
+
+## 🎥 Demo Video
+
+<a href="https://youtu.be/VyOawMrCB1g?si=7BubljRhsudGqG3s">
+  <img src="https://img.youtube.com/vi/VyOawMrCB1g/maxresdefault.jpg" width="400" alt="ChatterBox SRT Voice Demo">
+</a>
+
+**[▶️ Watch Full Demo](https://youtu.be/VyOawMrCB1g?si=7BubljRhsudGqG3s)**
+
+### [ShmuelRonen](https://github.com/ShmuelRonen/ComfyUI_ChatterBox_Voice) ChatterBox TTS Nodes
 
-### Enhanced ChatterBox TTS
 <div align="center">
   <img src="https://github.com/user-attachments/assets/4197818c-8093-4da4-abd5-577943ac902c" width="45%" alt="ChatterBox TTS Nodes" />
   <img src="https://github.com/user-attachments/assets/701c219b-12ff-4567-b414-e58560594ffe" width="45%" alt="ChatterBox Voice Capture" />
@@ -51,14 +66,6 @@ For comprehensive technical information, refer to the [SRT_IMPLEMENTATION.md](do
 * **Enhanced Chunking**: Intelligent text splitting with multiple combination methods
 * **Unlimited Text Length**: No character limits with smart processing
 
-## 🎥 Demo Video
-
-<a href="https://youtu.be/VyOawMrCB1g?si=7BubljRhsudGqG3s">
-  <img src="https://img.youtube.com/vi/VyOawMrCB1g/maxresdefault.jpg" width="400" alt="ChatterBox SRT Voice Demo">
-</a>
-
-**[▶️ Watch Full Demo](https://youtu.be/VyOawMrCB1g?si=7BubljRhsudGqG3s)**
-
 ## Features
 
 - 🎤 **ChatterBox TTS** - Generate speech from text with optional voice cloning
@@ -78,17 +85,20 @@ For comprehensive technical information, refer to the [SRT_IMPLEMENTATION.md](do
 **Get running in 5 minutes:**
 
 1. **Clone & Install**
+   
    ```bash
    cd ComfyUI/custom_nodes
    git clone https://github.com/diodiogod/ComfyUI_ChatterBox_SRT_Voice.git
    pip install -r ComfyUI_ChatterBox_SRT_Voice/requirements.txt
    ```
 
 2. **Download Models** (Required)
+   
    - Download from [HuggingFace ChatterBox](https://huggingface.co/ResembleAI/chatterbox/tree/main)
    - Place in `ComfyUI/models/chatterbox/`
 
 3. **Try a Workflow**
+   
    - Download: [ChatterBox Integration Workflow](example_workflows/Chatterbox%20integration.json)
    - Drag into ComfyUI and start generating!
 
@@ -181,26 +191,29 @@ ComfyUI/models/F5-TTS/
 
 **Available F5-TTS Models:**
 
-| Model | Language | Download | Size |
-|-------|----------|----------|------|
-| **F5TTS_Base** | English | [HuggingFace](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_Base) | ~1.2GB |
-| **F5TTS_v1_Base** | English (v1) | [HuggingFace](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_v1_Base) | ~1.2GB |
-| **E2TTS_Base** | English (E2-TTS) | [HuggingFace](https://huggingface.co/SWivid/E2-TTS/tree/main/E2TTS_Base) | ~1.2GB |
-| **F5-DE** | German | [HuggingFace](https://huggingface.co/aihpi/F5-TTS-German) | ~1.2GB |
-| **F5-ES** | Spanish | [HuggingFace](https://huggingface.co/jpgallegoar/F5-Spanish) | ~1.2GB |
-| **F5-FR** | French | [HuggingFace](https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced) | ~1.2GB |
-| **F5-JP** | Japanese | [HuggingFace](https://huggingface.co/Jmica/F5TTS) | ~1.2GB |
+| Model             | Language         | Download                                                                         | Size   |
+| ----------------- | ---------------- | -------------------------------------------------------------------------------- | ------ |
+| **F5TTS_Base**    | English          | [HuggingFace](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_Base)         | ~1.2GB |
+| **F5TTS_v1_Base** | English (v1)     | [HuggingFace](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_v1_Base)      | ~1.2GB |
+| **E2TTS_Base**    | English (E2-TTS) | [HuggingFace](https://huggingface.co/SWivid/E2-TTS/tree/main/E2TTS_Base)         | ~1.2GB |
+| **F5-DE**         | German           | [HuggingFace](https://huggingface.co/aihpi/F5-TTS-German)                        | ~1.2GB |
+| **F5-ES**         | Spanish          | [HuggingFace](https://huggingface.co/jpgallegoar/F5-Spanish)                     | ~1.2GB |
+| **F5-FR**         | French           | [HuggingFace](https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced) | ~1.2GB |
+| **F5-JP**         | Japanese         | [HuggingFace](https://huggingface.co/Jmica/F5TTS)                                | ~1.2GB |
 
 **Vocoder (Optional but Recommended):**
+
 ```
 ComfyUI/models/F5-TTS/vocos/
 ├── config.yaml
 ├── pytorch_model.bin
 └── vocab.txt
 ```
+
 Download from: [Vocos Mel-24kHz](https://huggingface.co/charactr/vocos-mel-24khz)
 
 **Complete Folder Structure:**
+
 ```
 ComfyUI/models/F5-TTS/
 ├── F5TTS_Base/
@@ -215,6 +228,7 @@ ComfyUI/models/F5-TTS/
 ```
 
 **Required Files for Each Model:**
+
 - `model_XXXXXX.safetensors` - The main model weights
 - `vocab.txt` - Vocabulary/tokenizer file (download from same HuggingFace repo)
 
@@ -238,6 +252,7 @@ ComfyUI/models/voices/
 ```
 
 **Voice Reference Requirements:**
+
 - **Audio files**: WAV format, 5-30 seconds, clean speech, 24kHz recommended
 - **Text files**: Exact transcription of what's spoken in the audio file
 - **Naming**: `filename.wav` + `filename.reference.txt` (preferred) or `filename.txt` (fallback)
@@ -360,17 +375,17 @@ ComfyUI/models/voices/
 
 ### Available Workflows
 
-| Workflow | Description | Files |
-|----------|-------------|-------|
-| **ChatterBox SRT** | SRT subtitle timing and TTS generation | [📁 JSON](example_workflows/Chatterbox%20SRT.json) • [🖼️ Preview](example_workflows/Chatterbox%20SRT.jpg) |
-| **ChatterBox Integration** | General ChatterBox TTS and Voice Conversion | [📁 JSON](example_workflows/Chatterbox%20integration.json) • [🖼️ Preview](example_workflows/Chatterbox%20integration.jpg) |
+| Workflow                   | Description                                 | Files                                                      |
+| -------------------------- | ------------------------------------------- | ---------------------------------------------------------- |
+| **ChatterBox SRT**         | SRT subtitle timing and TTS generation      | [📁 JSON](example_workflows/Chatterbox%20SRT.json)         |
+| **ChatterBox Integration** | General ChatterBox TTS and Voice Conversion | [📁 JSON](example_workflows/Chatterbox%20integration.json) |
 
 ### Coming Soon (Placeholders)
 
-| Workflow | Description | Status |
-|----------|-------------|--------|
-| **Audio Wave Analyzer + F5 Speech Edit** | Interactive waveform analysis for F5-TTS speech editing | [📁 JSON](example_workflows/👄%20F5-TTS%20Speech%20Editor%20Workflow.json) • 🖼️ **Screenshot Coming Soon** |
-| **F5-TTS SRT Workflows** | F5-TTS integration with SRT subtitle processing | 🚧 **Coming Soon** |
+| Workflow                                 | Description                                             | Status                                                                     |
+| ---------------------------------------- | ------------------------------------------------------- | -------------------------------------------------------------------------- |
+| **Audio Wave Analyzer + F5 Speech Edit** | Interactive waveform analysis for F5-TTS speech editing | [📁 JSON](example_workflows/👄%20F5-TTS%20Speech%20Editor%20Workflow.json) |
+| **F5-TTS SRT Workflows**                 | F5-TTS integration with SRT subtitle processing         | 🚧 **Coming Soon**                                                         |
 
 > **Note:** To use workflows, download the `.json` files and drag them directly into your ComfyUI interface. The workflows will automatically load with the proper node connections.
 

chatterbox_srt/__init__.py

@@ -4,7 +4,7 @@
 """
 
 # Version info
-__version__ = "3.0.11"
+__version__ = "3.0.12"
 __author__ = "Diogod"
 
 # Import the new SRT modules

core/__init__.py

@@ -4,7 +4,7 @@
 """
 
 # Version info
-__version__ = "3.0.11"
+__version__ = "3.0.12"
 __author__ = "Diogod"
 
 # Make imports available at package level

core/f5tts_model_manager.py

@@ -39,12 +39,15 @@ def _check_f5tts_availability(self):
         except ImportError:
             self.f5tts_available = False
 
-    def find_f5tts_models(self) -> List[Tuple[str, Optional[str]]]:
+    def find_f5tts_models(self, model_name: str = None) -> List[Tuple[str, Optional[str]]]:
         """
         Find F5-TTS model files in order of priority:
-        1. ComfyUI models/F5-TTS/ directory
+        1. ComfyUI models/F5-TTS/ directory (only matching model name if specified)
         2. HuggingFace download
         
+        Args:
+            model_name: Optional specific model name to search for
+        
         Returns:
             List of tuples containing (source_type, path) in priority order
         """
@@ -56,6 +59,10 @@ def find_f5tts_models(self) -> List[Tuple[str, Optional[str]]]:
             for item in os.listdir(comfyui_f5tts_path):
                 item_path = os.path.join(comfyui_f5tts_path, item)
                 if os.path.isdir(item_path):
+                    # If specific model name provided, only check matching folders
+                    if model_name and item.lower() != model_name.lower():
+                        continue
+                    
                     # Check if it contains model files
                     has_model = False
                     for ext in [".safetensors", ".pt"]:
@@ -111,12 +118,21 @@ def load_f5tts_model(self, model_name: str = "F5TTS_Base", device: str = "auto",
         if device == "auto":
             device = "cuda" if torch.cuda.is_available() else "cpu"
 
-        # Get available model paths
-        model_paths = self.find_f5tts_models()
+        # Get available model paths for specific model
+        model_paths = self.find_f5tts_models(model_name)
 
         model_loaded = False
         last_error = None
 
+        # Check if this model should be available locally
+        local_model_expected = False
+        comfyui_f5tts_path = os.path.join(folder_paths.models_dir, "F5-TTS")
+        if os.path.exists(comfyui_f5tts_path):
+            for item in os.listdir(comfyui_f5tts_path):
+                if item.lower() == model_name.lower() or model_name.lower() in item.lower():
+                    local_model_expected = True
+                    break
+        
         for source, path in model_paths:
             try:
                 cache_key = self.get_f5tts_model_cache_key(model_name, device, source, path)
@@ -133,6 +149,18 @@ def load_f5tts_model(self, model_name: str = "F5TTS_Base", device: str = "auto",
                     from chatterbox.f5tts import ChatterBoxF5TTS
                     model = ChatterBoxF5TTS.from_local(path, device, model_name)
                 elif source == "huggingface":
+                    # If a local model was expected but failed, don't fallback to HuggingFace
+                    if local_model_expected and last_error:
+                        print(f"❌ Model '{model_name}' found in local directory but failed to load")
+                        print(f"❌ Fallback to HuggingFace disabled for locally expected models")
+                        raise RuntimeError(f"Model '{model_name}' exists locally but failed to load. Please check the model files or use a different model.")
+                    
+                    # Check if model is available on HuggingFace
+                    from chatterbox.f5tts.f5tts import F5TTS_MODELS
+                    if model_name not in F5TTS_MODELS:
+                        print(f"❌ Model '{model_name}' not available on HuggingFace")
+                        raise RuntimeError(f"Model '{model_name}' is not available on HuggingFace. Please install it locally or use a different model.")
+                    
                     from chatterbox.f5tts import ChatterBoxF5TTS
                     model = ChatterBoxF5TTS.from_pretrained(device, model_name)
                 else:
@@ -168,9 +196,11 @@ def get_f5tts_model_source(self, model_name: str, device: str) -> Optional[str]:
         Returns:
             Model source string or None if not cached
         """
-        # Try to find in cache by checking different sources
-        for source in ["comfyui", "huggingface"]:
-            cache_key = self.get_f5tts_model_cache_key(model_name, device, source)
+        # Try to find in cache by checking different sources with their paths
+        model_paths = self.find_f5tts_models(model_name)
+        
+        for source, path in model_paths:
+            cache_key = self.get_f5tts_model_cache_key(model_name, device, source, path)
             if cache_key in self._f5tts_model_sources:
                 return self._f5tts_model_sources[cache_key]
 

core/import_manager.py

@@ -32,6 +32,7 @@ def __init__(self, node_dir: Optional[str] = None, is_dev: bool = True):
         self.import_status: Dict[str, Dict[str, Any]] = {
             "chatterbox_tts": {"available": False, "source": None, "error": None},
             "chatterbox_vc": {"available": False, "source": None, "error": None},
+            "f5tts": {"available": False, "source": None, "error": None},
             "srt_parser": {"available": False, "source": None, "error": None},
             "audio_timing": {"available": False, "source": None, "error": None},
         }
@@ -149,6 +150,41 @@ def import_chatterbox_vc(self) -> Tuple[bool, Optional[Any], str]:
                 self._log_debug(f"❌ ChatterboxVC not available: {system_error}")
                 return False, None, "none"
 
+    def import_f5tts(self) -> Tuple[bool, Any, str]:
+        """
+        Import F5-TTS with fallback handling.
+        
+        Returns:
+            Tuple of (success, f5tts_module, source)
+        """
+        module_key = "f5tts"
+        
+        # Return cached if available
+        if self.import_status[module_key]["available"]:
+            return True, self.loaded_modules[module_key], self.import_status[module_key]["source"]
+        
+        try:
+            # Try to import F5-TTS API
+            from f5_tts.api import F5TTS
+            
+            self.loaded_modules[module_key] = F5TTS
+            self.import_status[module_key] = {
+                "available": True,
+                "source": "system",
+                "error": None
+            }
+            self._log_debug("✅ F5-TTS loaded from system package")
+            return True, F5TTS, "system"
+            
+        except ImportError as error:
+            self.import_status[module_key] = {
+                "available": False,
+                "source": None,
+                "error": str(error)
+            }
+            self._log_debug(f"❌ F5-TTS not available: {error}")
+            return False, None, "none"
+    
     def import_srt_modules(self) -> Tuple[bool, Dict[str, Any], str]:
         """
         Import SRT-related modules with multiple fallback strategies.
@@ -210,11 +246,11 @@ def import_srt_modules(self) -> Tuple[bool, Dict[str, Any], str]:
                     "source": "direct_file",
                     "error": None
                 }
-                self._log_debug("✅ SRT modules loaded from direct files")
+                # SRT modules are bundled - no need to show success message
                 return True, modules, "direct_file"
 
             except Exception as file_error:
-                self._log_debug(f"❌ Failed to load SRT from files: {file_error}")
+                self._log_debug(f"❌ SRT modules failed to load (bundled files corrupted?): {file_error}")
 
         # Strategy 2: Try bundled package import
         if os.path.exists(self.bundled_chatterbox_dir):
@@ -299,7 +335,7 @@ def import_srt_modules(self) -> Tuple[bool, Dict[str, Any], str]:
                 "source": None,
                 "error": f"All import strategies failed. Last error: {system_error}"
             }
-            self._log_debug(f"❌ SRT modules not available: {system_error}")
+            self._log_debug(f"❌ SRT modules critically failed to load: {system_error}")
             return False, self._create_dummy_srt_modules(), "none"
 
     def _create_fallback_audio_timing(self) -> Dict[str, Any]:

core/model_manager.py

@@ -14,10 +14,12 @@
 # Try imports first to populate availability status
 tts_success, ChatterboxTTS, tts_source = import_manager.import_chatterbox_tts()
 vc_success, ChatterboxVC, vc_source = import_manager.import_chatterbox_vc()
+f5tts_success, F5TTS, f5tts_source = import_manager.import_f5tts()
 
 # Set availability flags
 CHATTERBOX_TTS_AVAILABLE = tts_success
 CHATTERBOX_VC_AVAILABLE = vc_success
+F5TTS_AVAILABLE = f5tts_success
 USING_BUNDLED_CHATTERBOX = tts_source == "bundled" or vc_source == "bundled"
 
 

images/AllNodesShowcase.png

@@ -1,5 +1,5 @@
 # Version and constants
-VERSION = "3.0.11"
+VERSION = "3.0.12"
 IS_DEV = False  # Set to False for release builds
 VERSION_DISPLAY = f"v{VERSION}" + (" (dev)" if IS_DEV else "")
 SEPARATOR = "=" * 70