- Remove Speed column (unnecessary for overview)
- Remove 🎯 emoji from title (too many emojis)
- Add ChatterBox to featured engines (now shows 7 engines)
- Created comprehensive YAML source of truth for all TTS engines
- Implemented Python generator for 3 documentation tables:
* ENGINE_COMPARISON.md - Main engine overview with capabilities
* LANGUAGE_SUPPORT.md - Detailed language support matrix
* FEATURE_COMPARISON.md - Feature capabilities comparison
- YAML captures all engine metadata without information loss
- Tables auto-generated via scripts/generate_engine_tables.py
- Added flag emojis to language support table for easy scanning
- Speed performance fixes: F5-TTS marked as "Very Fast"
Fixed 'dict' object has no attribute 'cpu' error when using Voice Designer
voices with TTS Text node.
## Root Cause
Voice Designer and Character Voices nodes output unified NARRATOR_VOICE format:
{
"audio": {"waveform": tensor, "sample_rate": 24000},
"audio_path": "...",
"reference_text": "...",
...
}
But TTS Text node was wrapping this AGAIN when creating voice_mapping:
{
"waveform": audio_tensor, # audio_tensor was already a dict!
"sample_rate": 24000,
"text": "..."
}
This created triple-nested structure that broke audio hashing.
## Fixes Applied
**TTS Text Node** (nodes/unified/tts_text_node.py):
- Extract actual waveform tensor from audio dict before creating voice_mapping
- Applied to all 6 places where audio_tensor is used:
- Narrator voice mapping (line 1151)
- Character ICL fallback (line 1183)
- Character x_vector fallback (line 1217)
- Character no-text fallback (line 1220)
- Character no-audio fallback (line 1237)
- Pattern: Check if audio_tensor is dict, extract waveform/sample_rate if so
**Qwen3-TTS Adapter** (engines/adapters/qwen3_tts_adapter.py):
- Extract inner audio dict before passing to hash function
- Changed from passing full voice_ref to passing voice_ref['audio']
**Audio Hash Utility** (utils/audio/audio_hash.py):
- Added nested structure handling with fallback
- Detects Character Voices format {"audio": {...}} vs direct format
- Enhanced debug logging to diagnose structure issues
## Testing
- Voice Designer → TTS Text: Works without hash error
- Character Voices → TTS Text: Works without hash error
- Audio hashing generates stable keys for caching
- Both VoiceDesign and traditional voices function correctly
Added edit tag extraction and batch processing for Higgs Audio TTS and SRT processors following the established pattern from VibeVoice and Step Audio EditX.
Key changes:
- Extract edit tags at top level before pause processing to keep nested functions returning tensors
- Apply edit post-processing after all audio generation completes
- For SRT: batch process all subtitle edits at end instead of per-subtitle
- Fix CUDA graph crash: detect original engine for stateless wrappers and refuse unloading when CUDA graphs enabled
- Store original_engine in ModelInfo to track Higgs even when masked as stateless_tts
- Update Higgs handler to check correct attribute paths for _cuda_graphs_enabled flag
Files modified:
- nodes/higgs_audio/higgs_audio_tts_processor.py: Add edit tag extraction and post-processing
- nodes/higgs_audio/higgs_audio_srt_processor.py: Batch edit processing for all subtitles
- utils/models/comfyui_model_wrapper/base_wrapper.py: Track original_engine for masked engines
- utils/models/comfyui_model_wrapper/model_manager.py: Store original engine when masking
- utils/models/comfyui_model_wrapper/engine_handlers/higgs_audio_handler.py: Refuse unload when CUDA graphs enabled
- docs/Dev reports/SRT_Edit_Tag_Batch_Processing_Pattern.md: Mark Higgs as implemented
Fixed inefficient per-subtitle edit processing that caused multiple engine loads.
Now all edit processing happens in a single batch after all subtitles are generated.
Changes:
- VibeVoice SRT: Collects all segments with edit_tags, applies edits once at end
- Step Audio EditX SRT: Same batching pattern, skips edits in _process_character_switching when in SRT mode
- Step processor: Added check to only apply edits when NOT in SRT mode
- Subtitle processing functions: Return segment dicts instead of applying edits directly
Benefits:
- Edit engine loads ONCE instead of once per subtitle
- Significantly faster SRT generation with edit tags
- Less VRAM thrashing from repeated model loading/unloading
- Maintains same quality output
Added dev report documenting the pattern for future engine implementations.
Major changes:
1. Post-processor now uses Audio Editor node instead of calling engine directly
- Inherits progress bars, caching, tested code
- Much simpler and more maintainable
2. Fixed unified model interface usage across Step Audio EditX
- Adapter now loads via unified_model_interface.load_model()
- Audio Editor node now loads via unified_model_interface.load_model()
- Both use model_type="tts" for consistent cache keys
- Prevents duplicate model loading (was loading twice before)
3. Fixed pause tag + edit tag interaction
- Pause tags split FIRST, then edit tags extracted per segment
- Allows: "Hello <Laughter> [pause:1] World <Sigh>"
- Laughter applies to "Hello", Sigh applies to "World"
4. Added lesson to fails document
- All engines must use unified interface in ALL code paths
- Cache key must match across adapters/nodes/processors
Bug fixes:
- Missing Dict import in post-processor
- Import path for Audio Editor node (use importlib)
- Progress bars now work during editing
Files modified:
- utils/audio/edit_post_processor.py - refactored to use Audio Editor node
- nodes/step_audio_editx/step_audio_editx_processor.py - pause handling
- engines/adapters/step_audio_editx_adapter.py - unified interface
- nodes/step_audio_editx_special/step_audio_editx_audio_editor_node.py - unified interface
- docs/Dev reports/fails_to_avoid_TTS_Engine_Implementation.md - added lesson
Added support for inline edit tags in TTS text that automatically apply
Step Audio EditX edits to generated audio from ANY engine.
Syntax examples:
- <Laughter:2> - paralinguistic with iterations
- <emotion:happy:1> - emotion edit
- <style:whisper:3> - style edit
- <speed:faster> - speed adjustment
- <Laughter:2|style:whisper> - multiple effects
Key changes:
- Extended step_audio_editx_special_tags.py with EditTag dataclass and iteration parsing
- Created edit_post_processor.py for centralized post-TTS edit application
- Integrated into Step Audio EditX processor with proper pause tag handling
- Pause tags split FIRST, then edit tags extracted per pause-segment
- Reuses already-loaded engine to avoid duplicate loading
Flow:
1. Parse text, split by pause tags first
2. Extract edit tags from each pause-delimited segment
3. Generate TTS with clean text (tags stripped)
4. Post-processor applies edits to segments with tags
5. Assemble final audio
Currently working for Step Audio EditX TTS and SRT nodes.
Replace complex weight restoration workaround with a simple one-line config fix.
The root cause: Step-Audio-EditX model config was missing 'tie_word_embeddings'
setting, so transformers 4.54+ defaulted to True and tied lm_head to embed_tokens
even though the checkpoint has different weights for each.
Solution: Add 'tie_word_embeddings': false to config.json to prevent tying.
This is much simpler and cleaner than the previous safetensors weight restoration
approach. One line in config.json fixes the issue for all transformers versions.
- Add step_audio_editx to PARAMETER_ENGINES for seed and temperature
- Fix engine node tooltips: parameters ARE used in clone mode (not hardcoded)
- Add reference implementation paths to implementation plan
- Update fails doc with latest lessons learned
Make both engines follow ChatterBox 23-Lang modular pattern:
**Step Audio EditX:**
- Update combine_audio_segments() to use ChunkCombiner with return_info=True
- Return (audio, chunk_info) tuple when requested
- Fix single segment shape handling (ensure 2D [channels, samples])
**IndexTTS:**
- Add combine_audio_segments() method using ChunkCombiner
- Update process_text() to accept return_info parameter
- Build chunk_info from text segments and return timing data
**Unified Node:**
- Call both engines with return_info=True
- Use ChunkTimingHelper.enhance_generation_info() for detailed reports
- Clean text without tags before calculating length
**Documentation:**
- Add generation_info consistency requirement to fails document
- Document correct pattern: ChunkCombiner + ChunkTimingHelper
- Note wrong pattern: inline torch.cat without timing
Now both engines provide detailed timing reports like F5-TTS and ChatterBox.
Models should only unload when explicitly requested (Clear VRAM button) or when
switching engines - NOT automatically after generation completes.
__del__ was causing models to unload immediately after wrapper instance goes
out of scope, preventing model reuse between generations.
Pattern: F5-TTS and ChatterBox don't have __del__, only Index2 and StepAudio had it.
Removed to match correct behavior.
- Configure character parser with available characters and language defaults like IndexTTS
- Add characters from text tags to available_characters to prevent fallback to "narrator"
- Add fallback voice mapping entries for characters without voice files
- Update fails document with character switching implementation lessons
Implemented Step Audio EditX integration with the following components:
Engine Implementation:
- Bundled Step Audio EditX reference code in step_audio_editx_impl/
- Created engine wrapper (step_audio_editx.py) with clone/edit methods
- Created adapter (step_audio_editx_adapter.py) for unified interface
- Created processor (step_audio_editx_processor.py) for TTS Suite integration
Model Management:
- Created downloader (step_audio_editx_downloader.py) for:
- Main Step-Audio-EditX model (3B LLM + CosyVoice vocoder)
- Step-Audio-Tokenizer files (linguistic_tokenizer.npy, speech_tokenizer_v1.onnx)
- FunASR-Paraformer model with correct config for bundled funasr_detach
- Fixed FunASR config to use bundled class names (ParaformerStreaming, WavFrontendOnline, SpecAugLFR)
- Added auto-download for all required models on first use
- Updated unified_model_interface.py to auto-download Step-Audio-EditX components
Node Configuration:
- Created Step Audio EditX engine config node
- Registered in nodes.py and unified TTS text node
Known Issues:
- LLM generation hangs during inference despite:
- torch.no_grad() wrapper
- torch.cuda.synchronize()
- Eager attention mode (Step1ForCausalLM doesn't support SDPA)
- Reduced max_new_tokens
- Removed logits processor
- Model loads successfully, all components initialized correctly
- Issue appears to be with transformers.generate() call itself
- Requires further investigation of Step1ForCausalLM compatibility
Files Modified:
- nodes.py: Added Step Audio EditX registration
- requirements.txt: Added FunASR dependencies
- utils/models/unified_model_interface.py: Added Step Audio EditX factory
- Various Step Audio EditX implementation files
Model Downloads:
- Step-Audio-EditX: 7GB (3B LLM + vocoder)
- FunASR-Paraformer: 881MB (from custom HF repo with fixed config)
- Step-Audio-Tokenizer: Bundled with main model download
MAJOR: IndexTTS-2 TTS engine integration
- Core IndexTTS engine with unified model interface integration
- Auto-downloader for HuggingFace models + GitHub source code
- Engine adapter with emotion support [Alice:angry_bob] syntax
- Cache integration for IndexTTS-2 parameters
- Factory registration for proper model management
MAJOR: Character parser modularization (930 → 300 lines each)
- Split into base_parser.py, language_resolver.py, segment_processor.py, validation.py
- Added emotion support with backward compatibility
- New split_by_character_with_emotions() method for advanced engines
- Flexible tag parsing: [de:Alice:angry_bob] support
- Language disambiguation to avoid Alice vs language code conflicts
- Full backward compatibility maintained
FEATURES:
- IndexTTS-2 emotion disentanglement (speaker vs emotion separation)
- Duration control and precise voice cloning
- Multi-modal emotion control (audio refs, text, vectors)
- Character switching with emotion references
- All official IndexTTS-2 parameters exposed
DOCS: Implementation plan and architectural TODO items added
Update VibeVoice 7B to official Microsoft repository
Technical details:
- Change repo from WestZhang/VibeVoice-Large-pt to microsoft/VibeVoice-Large
- Update documentation and downloader references
- Maintain backward compatibility with existing installations
Fix F5-TTS model name case sensitivity issue
- Fix uppercase V1 being rejected in model validation
- Add regex normalization for version numbers (V1 -> v1)
- Ensure backward compatibility with saved workflows
Fix Higgs Audio model management with CUDA Graph compatibility toggle
Technical implementation:
- Add enable_cuda_graphs parameter to resolve CUDA Graph vs model unloading conflict
- Implement DynamicCache support for safe memory management mode
- Fix DynamicCache compatibility issues (reset, seq_length, copying)
- Add conditional cache creation and cleanup logic
- Update tooltip with accurate performance trade-offs (12 vs 55+ tok/s)
- Fix HiggsAudioEngineNode return type from HIGGS_AUDIO_ENGINE to TTS_ENGINE for unified node compatibility
- Remove duplicated parameters: seed, enable_cache, enable_chunking, max_tokens_per_chunk, silence_between_chunks_ms
- Keep engine-specific parameters: max_new_tokens (generation limit), voice_preset, audio_priority, system_prompt
- Update TTS Text node to pass max_chars_per_chunk to Higgs Audio adapter
- Maintain character-based chunking via ImprovedChatterBoxChunker with token-to-char conversion
- Preserve clean separation: universal parameters in TTS Text, engine-specific in Engine nodes
The Higgs Audio Engine Node now properly connects to unified TTS Text and TTS SRT nodes
while maintaining engine-specific generation parameters that other engines don't have.
- Created StatelessChatterBoxWrapper to eliminate shared state corruption
- Wrapper calculates conditions fresh for each generation (no self.conds)
- Updated streaming processor to use stateless wrapper with batch_size control
- Modified streaming model manager to provide stateless wrappers
- Updated SRT nodes to use stateless generation in streaming mode
- Added comprehensive tensor detaching to prevent autograd issues
- Initial testing shows parallel generation working without immediate crashes
Note: Requires extensive testing to confirm stability with high worker counts
- Create universal streaming module in utils/streaming/
- Implement StreamingCoordinator to replace all format-specific routers
- Create universal StreamingSegment data structure (no more format conversions)
- Implement UniversalWorkQueueProcessor for engine-agnostic parallel processing
- Add ChatterBox streaming adapter preserving all existing functionality
- Add F5-TTS streaming adapter with language model switching support
- Document complete streaming integration plan in F5TTS_STREAMING_INTEGRATION_PLAN.md
This creates the foundation for eliminating the current spaghetti code where
each node type needs its own router and format conversions. The universal
system works with any engine through adapters while preserving all existing
functionality.
- Remove orphaned dynamic_worker_manager.py (never imported/used)
- Update PROJECT_INDEX.md to reflect file removal
- Enhance STREAMING_ARCHITECTURE.md with feasibility analysis for F5-TTS
- Document that StreamingWorkQueueProcessor is the active implementation
- Confirm streaming architecture is engine-extensible via adapter pattern
- Make separate commit/changelog descriptions the default (no more broken auto-categorization)
- Add auto-increment support: use 'patch', 'minor', 'major' instead of manual version numbers
- Fix categorization algorithm that was misclassifying bug fixes as Added items
- Add simple mode to bypass automatic categorization entirely
- Fix manual changelog entry for v3.4.2 (was previously miscategorized)
- Update documentation with new recommended usage patterns
- Enhanced keyword matching with domain-specific terms for better categorization
- Added context-aware parsing for emoji section headers
- Fixed title skipping to prevent main description from being categorized
- Changed default from 'Fixed' to 'Added' for feature releases
- Corrected v3.4.0 changelog formatting manually
- Updated version management guide with script improvements and lessons learned
- Replace confusing Python code snippets with actual ComfyUI usage instructions
- Convert Video Dubbing, Presentation Audio, and Voice Cloning examples to ComfyUI parameter settings
- Add clear 'Best for' descriptions and use cases for each timing mode
- Maintain Python code in Technical Implementation and API sections (appropriate for developers)
- Improve user experience by showing actual workflow steps instead of code
- Replace multi-line string with explicit newline characters in code example
- Prevents markdown rendering issues with nested quotes in code blocks
- Improves code clarity and cross-platform compatibility
Improvements:
- Fix code block formatting and typos (high-quality??, Lowesr quality, timming)
- Add comprehensive table of contents with anchor links
- Reorganize structure: Quick Start → Quick Reference → Usage → Technical Details
- Move examples and quick start to top for better user experience
- Add professional quick reference tables for timing modes and parameters
- Enhance API reference section with better code examples
- Improve troubleshooting section with clear problem/solution format
- Polish language and maintain professional tone throughout
- Add visual hierarchy with emojis and better formatting
- Backup original file as SRT_IMPLEMENTATION_OLD.md
The document now serves both as quick reference for experienced users and comprehensive guide for newcomers.
- Finalized F5-TTS integration with full node implementation
- Completed Audio Wave Analyzer with interactive waveform visualization
- Enhanced documentation and user guides
- Version bump to 3.0.0 reflecting major feature additions
- Renamed '🎵 Audio Analyzer' to '🌊 Audio Wave Analyzer' throughout project
- Updated all node display names, tooltips, documentation, and web interface
- Preserved class names and internal identifiers for ComfyUI compatibility
- Fixed nfe_step bug in F5-TTS nodes: limited max value to 71 to prevent ODE solver issues
- Added validation clamping and warning messages in F5-TTS Node and F5-TTS Edit Node
- Updated tooltips to warn about ODE solver issues above 71
diodiogod