diodiogod-TTS-Audio-Suite

923 Commits 25 Branches 22 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
diodiogod	daf54de61d	Version 4.11.19 Optimize startup performance with lazy loading and async checks Engine node optimizations: - Replace heavy engine imports in INPUT_TYPES with file-reading-only model discovery - Remove blocking module loads from node initialization - Reconstruct discovery logic for all 7 engine nodes: VibeVoice, F5-TTS, Higgs, ChatterBox, ChatterBox 23-Lang, IndexTTS, RVC - Each engine now scans model folders without importing engine modules Voice discovery and dependency improvements: - Implement persistent voice character discovery cache in .cache folder - Add background refresh thread for cache updates - Move dependency checking to async background thread (2-second delay) - Prevent blocking initialization on startup - Print diagnostic messages after ComfyUI loads	2025-10-23 23:34:35 -03:00
diodiogod	d11db08134	Version 4.9.11 Fix faiss circular import crash in Docker environments Technical fix: - Add exception handling for AttributeError in dependency checker - Handle faiss Float32 circular import issue in containerized environments - Gracefully detect faiss availability despite import problems - Prevent startup crashes in Docker/OpenSUSE setups	2025-09-17 17:02:47 -03:00
diodiogod	2acb9be259	Fix Higgs Audio 2 engine integration issues - Fixed engine initialization issue where adapter never called initialize_engine - Fixed model configuration key mismatch (generation_repo vs generation_model) - Fixed tokenizer download file name (model.pth vs pytorch_model.bin) - Fixed tensor dimension issues for ComfyUI audio output format - Added comprehensive multi-speaker mode system with three options: * Custom Character Switching: Use [Alice], [Bob] with character voice files * Native Multi-Speaker (System Context): Use [SPEAKER0], [SPEAKER1] with opt_second_narrator * Native Multi-Speaker (Conversation): Same as above but conversation history mode - Removed audio_priority widget, now follows standard TTS priority logic - Fixed mode selection bug where config was read from wrong object - Added proper audio format handling for Character Voices in native modes - Fixed pause tag support in all modes including native multi-speaker - Improved tooltips to clarify mode requirements and text formats	2025-08-19 16:25:44 -03:00

Author

SHA1

Message

Date

diodiogod

daf54de61d

Version 4.11.19

Optimize startup performance with lazy loading and async checks

Engine node optimizations:
- Replace heavy engine imports in INPUT_TYPES with file-reading-only model discovery
- Remove blocking module loads from node initialization
- Reconstruct discovery logic for all 7 engine nodes: VibeVoice, F5-TTS, Higgs, ChatterBox, ChatterBox 23-Lang, IndexTTS, RVC
- Each engine now scans model folders without importing engine modules

Voice discovery and dependency improvements:
- Implement persistent voice character discovery cache in .cache folder
- Add background refresh thread for cache updates
- Move dependency checking to async background thread (2-second delay)
- Prevent blocking initialization on startup
- Print diagnostic messages after ComfyUI loads

2025-10-23 23:34:35 -03:00

diodiogod

d11db08134

Version 4.9.11

Fix faiss circular import crash in Docker environments

Technical fix:
- Add exception handling for AttributeError in dependency checker
- Handle faiss Float32 circular import issue in containerized environments
- Gracefully detect faiss availability despite import problems
- Prevent startup crashes in Docker/OpenSUSE setups

2025-09-17 17:02:47 -03:00

diodiogod

2acb9be259

Fix Higgs Audio 2 engine integration issues

- Fixed engine initialization issue where adapter never called initialize_engine
- Fixed model configuration key mismatch (generation_repo vs generation_model)
- Fixed tokenizer download file name (model.pth vs pytorch_model.bin)
- Fixed tensor dimension issues for ComfyUI audio output format
- Added comprehensive multi-speaker mode system with three options:
  * Custom Character Switching: Use [Alice], [Bob] with character voice files
  * Native Multi-Speaker (System Context): Use [SPEAKER0], [SPEAKER1] with opt_second_narrator
  * Native Multi-Speaker (Conversation): Same as above but conversation history mode
- Removed audio_priority widget, now follows standard TTS priority logic
- Fixed mode selection bug where config was read from wrong object
- Added proper audio format handling for Character Voices in native modes
- Fixed pause tag support in all modes including native multi-speaker
- Improved tooltips to clarify mode requirements and text formats

2025-08-19 16:25:44 -03:00