nodes/diodiogod-TTS-Audio-Suite
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,649 Commits 25 Branches 22 Tags
codex/audio-cpp-integration
Commit Graph
17 Commits
Author SHA1 Message Date
diodiogod b09e5023b5 Add DramaBox LoRA training and adapter loading 2026-08-09 23:50:59 -03:00
diodiogod 517d11ed4c Add DramaBox and ChatterBox V3 support 
- Integrate DramaBox with unified TTS and SRT generation, duration targeting, prompt templates, memory strategies, FP8, compile, and silence diagnostics
- Add ChatterBox 23-Lang V3 checkpoint support and artifact handling
- Extend parameter switching, generated-audio caching, tag editor controls, model downloads, and engine registration
- Add user documentation, engine metadata, generated comparison tables, and FL-MCP launcher reliability updates
 2026-07-25 11:38:52 -03:00
diodiogod 3d7e8dfaa1 Version 5.5.1 
Fix Step Audio EditX generation and runtime compatibility

Technical details:
- Restore the correct Step prompt, token layout, untied audio head, and memory-safe attention behavior
- Add shared and dedicated Transformers 4 runtime routing with worker progress reporting
- Preserve runtime selection across TTS, SRT, caching, and inline audio editing
- Fix character voice handling, empty audio validation, sample-rate interface, and deprecated dependency calls
 2026-07-18 20:38:56 -03:00
diodiogod 97f4a0c365 Add unified MOSS audio generation workflows 2026-07-16 12:35:01 -03:00
diodiogod 9081d3c22a Add Fish Audio S2 engine and fix VibeVoice speaker remap 2026-07-06 23:35:13 -03:00
diodiogod af13209b47 Add OmniVoice engine with native SRT duration targeting 2026-06-18 22:23:32 -03:00
diodiogod cb6dfe3a11 Add Dots TTS engine integration 2026-06-14 15:27:58 -03:00
diodiogod a42f4d3083 Resume Higgs Audio v3 on transformers 5 2026-06-09 19:04:57 -03:00
diodiogod f75837834e Add Higgs Audio shared isolation runtime 2026-06-08 22:20:18 -03:00
diodiogod 53df881108 Polish Qwen shared isolation runtime 2026-06-07 11:16:23 -03:00
diodiogod 14c32a96d1 Add Qwen3-TTS shared isolation runtime 2026-06-06 22:26:45 -03:00
diodiogod 2b61bafd73 Add shared VibeVoice isolation runtime 2026-06-06 15:09:27 -03:00
diodiogod 5fd7ecbea2 Add unified MOSS training pipeline and dataset tooling 2026-05-24 16:45:10 -03:00
diodiogod 2b69130a42 Add MOSS-TTS engine family with native TTSD support (#295) 
* docs: add new engine integration guide flow

* docs: link new engine guide navigation

* docs: clarify SRT is required for TTS engines

* docs: document SRT reuse of TTS processor

* docs: move new engine guide link below timeline

* Add MOSS-TTS engine integration

* docs: add reference input mode to engine research

* Add MOSS-TTS engine checkpoint

* Refine MOSS prompt fields and parameter switching

* Refine MOSS prompt field warnings and caching

* Improve MOSS inline edit handling and VRAM handoff

* Improve MOSS native dialogue mapping and UI

* docs: add long-form model analysis and VibeVoice reference

* Improve MOSS TTSD chunking, interrupts, and SRT mapping

* Refine MOSS mapping, device checks, and metadata

* Make MOSS native incompatibilities hard-fail

* Document MOSS native hard-fail compatibility rules
 2026-05-18 16:42:53 -03:00
diodiogod 4521ffbc79 Add unified RVC training workflow and improve RVC UX 2026-04-05 11:09:06 -03:00
diodiogod c709f129fc Version 4.23.0 
Add Granite ASR engine and expand unified ASR support

Implementation details:
- Add Granite ASR engine node, adapter, runtime, and unified downloader integration
- Reuse the Qwen forced aligner for optional custom Granite timestamps and SRT output
- Expose engine-side ASR translation target and prompt templates for Granite and Qwen
- Fix SRT overflow splitting so subtitle text is no longer silently dropped
- Update README and engine metadata for the expanded ASR lineup
 2026-03-16 23:58:56 -03:00
diodiogod a8c62f2307 TIER 3: Complete architecture standardization for model loading 
Implement standardized factory infrastructure enabling future engines:

1. ModelLoadConfig dataclass - Single canonical config class for all factories
   - Replaces duplicate UnifiedModelConfig
   - Contains device, model_name, language, model_path, repo_id, additional_params
   - Device resolution in __post_init__ for consistency

2. Engine capability registry - Data-driven engine specifications
   - Defines supports_voice_conversion, multilingual_model_switching, corruption recovery
   - Enables generic error handling without hardcoded engine checks
   - Covers all 7 TTS engines + IndexTTS-2

3. Fallback handler utility - Reusable fallback chain for graceful degradation
   - Try local → download → fallback language pattern
   - Eliminates duplicate fallback code across engines
   - Used by future engines automatically

4. Exception hierarchy - Standardized error types
   - TTSModelLoadingError base class
   - Specific types: NotFoundError, DeviceError, FormatError, InitializationError, LanguageNotSupportedError

Architecture benefits:
- All 8 factories now accept config: ModelLoadConfig instead of **kwargs
- Type-safe, clear factory signatures
- Future engines follow identical pattern
- No deprecated code left behind
- ComfyUI model manager handles both old and new patterns

Testing:
- All 7 TTS engines working correctly
- Device switching and caching working
- No syntax errors, all files compile

Note: SmartModelLoader still in use (Tier 2 cleanup pending) causing benign double-loads on some engines.
 2025-11-14 10:10:52 -03:00