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
542 Commits
Author SHA1 Message Date
diodiogod 5a28a46010 Add audio.cpp multi-task support 2026-08-13 21:41:16 -03:00
diodiogod 4a99f15851 Add audio.cpp TTS engine integration 2026-08-12 11:50:10 -03:00
diodiogod 08e8e8c884 Version 5.8.1 
Add MOSS community full-checkpoint support

Implementation details:
- Add the LAION MOSS-TTS v1.5 Voice Acting 8B community model to the engine dropdown and downloader
- Discover compatible local MOSS full checkpoints and resolve architecture from config.json
- Enable the LAION Delay checkpoint in the existing LoRA training pipeline
- Reject unsupported local MOSS layouts instead of assuming Local Transformer
- Address issue #340
 2026-08-11 23:42:44 -03:00
diodiogod 2bc4c2a18d Add IndexTTS 2.5 support 2026-08-11 23:08:35 -03:00
diodiogod bf7d83f26e Improve DramaBox LoRA runtime reuse and documentation 2026-08-10 11:10:23 -03:00
diodiogod b09e5023b5 Add DramaBox LoRA training and adapter loading 2026-08-09 23:50:59 -03:00
diodiogod 127bfe32fc Version 5.6.4 
Add MOSS training folder dataset import

Implementation details:
- Accept paired audio and transcript folders in MOSS Dataset Prep
- Generate deterministic cached JSONL manifests without changing existing manifest behavior
- Add optional recursive scanning and validation-folder support
- Address issue #340
 2026-08-03 08:10:33 -03:00
diodiogod 48608775e0 Version 5.6.2 
Handle incompatible FlashAttention installs in F5-TTS

Technical details:
- Validate optional FlashAttention submodules before enabling the backend
- Keep F5-TTS on PyTorch attention when FlashAttention is partial or incompatible
- Improve the explicit FlashAttention backend error
- Address issue #334
 2026-07-30 19:50:54 -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 ccbc721c2d Improve sound effect timeline handling and compile caching 2026-07-17 01:33:18 -03:00
diodiogod d8bf3dc865 Fix moss soundeffect v2 dtype handling and suppress harmless Inductor Ro 2026-07-16 22:46:14 -03:00
diodiogod 0c5201ebf3 Improve MOSS model-specific controls 2026-07-16 22:30:07 -03:00
diodiogod 4a1bfd7b75 Merge branch 'main' into codex/unified-voice-design-and-saving 2026-07-16 14:03:31 -03:00
diodiogod 97f4a0c365 Add unified MOSS audio generation workflows 2026-07-16 12:35:01 -03:00
diodiogod 4ccc0aa5ee Unify Hugging Face download output 2026-07-15 22:52:14 -03:00
diodiogod 198662124c Support MOSS-TTS v1.5 LoRA training 2026-07-15 22:27:19 -03:00
diodiogod 08916ea598 Fix MOSS download output and model lifecycle 2026-07-15 21:39:58 -03:00
diodiogod 08b50473f5 Repair Fish and VibeVoice runtime paths for issue 322 
- Restore the removed TorchAudio backend probe before Fish initializes
- Resolve local VibeVoice models in the parent ComfyUI process
- Pass absolute model paths into isolated VibeVoice workers
- Add regression coverage for both compatibility paths
 2026-07-15 15:13:27 -03:00
diodiogod 4937ff9a5b Repair engine runtime installation for issue 322 
- Restore Fish S2 implicit namespace packages correctly
- Use the Dots TTS normalizer fallback for incomplete tn installations
- Remove conflicting WebRTC dependencies from VibeVoice runtimes
- Rebuild isolated runtimes when profile definitions change
- Add focused installer regression coverage
 2026-07-15 06:53:52 -03:00
diodiogod da88ced2a5 Improve voice design saving and OmniVoice language handling 2026-07-15 06:25:17 -03:00
diodiogod f344099e3b Add unified voice design and character saving 2026-07-15 00:22:32 -03:00
diodiogod 12ce9be0c0 Fix RVC HuBERT auto-selection 
Address issue #319 by deferring automatic HuBERT selection until the RVC checkpoint dimension is known.

- Match 768-dimensional voices with ContentVec automatically
- Match verified 1024-dimensional voices with HuBERT Large automatically
- Warn that HuBERT Large training lacks a compatible pretrained generator
- Recommend ContentVec 768 for reliable RVC training and inference
 2026-07-14 18:58:58 -03:00
diodiogod 764e28a1aa Add HuBERT Large RVC training support 2026-07-14 17:38:30 -03:00
diodiogod d3ab465983 Guard RVC training against HuBERT dimension mismatch 2026-07-14 16:41:03 -03:00
diodiogod 516ab1595f Version 5.4.11 
Address issue #319 RVC Dataset Prep cache rebuild

Technical details:
- Rebuild RVC prepared datasets when the filelist or required feature artifacts are missing
- Preserve filelist-only refresh for complete stale caches
- Prevent first-run dataset preparation from skipping HuBERT feature extraction
 2026-07-13 22:15:09 -03:00
diodiogod d0430d846d Version 5.4.8 
Address CosyVoice3 ROCm precision handling (issue #323)

Technical details:
- Run the bundled Qwen LLM with BF16 autocast on ROCm
- Keep the CosyVoice3 flow model and HiFT vocoder in FP32
- Disable unsupported TensorRT loading on ROCm
- Forward LLM worker failures instead of decoding empty tokens
 2026-07-13 11:59:53 -03:00
diodiogod 7ff08f6070 Version 5.4.7 
Enhance Character Voices reference editing

Implementation details:
- Add automatic transcription loading and workflow-local overrides
- Add modular trim-range controls and reference_audio_only output
- Preserve source provenance while preventing stale path fallbacks
- Unify tensor-first voice reference resolution across affected engines

Fixes #318
 2026-07-13 11:54:19 -03:00
diodiogod 6da635cf74 Sync IndexTTS updates and document editor features 2026-07-11 16:24:08 -03:00
diodiogod df3a4cb2cf Blend IndexTTS audio and vector emotions 2026-07-11 01:39:43 -03:00
diodiogod 06003e0b3a Fix IndexTTS emotion and character routing 2026-07-11 01:24:38 -03:00
diodiogod 068c3f1f1e Add IndexTTS-2 inline emotion controls 2026-07-10 23:21:53 -03:00
diodiogod b31b31b89f Version 5.4.2 
Address issue #312 with MPS-safe RVC tensor typing

Technical details:
- Keep RVC pitch indices integer on Apple MPS devices.
- Normalize phone features to the linear layer weight dtype.
- Normalize pitch values to torch.long at the encoder boundary.
- Preserve CUDA half-precision compatibility.
 2026-07-10 14:25:59 -03:00
diodiogod 282616ebe1 Finalize Fish Audio S2 integration 2026-07-10 09:09:17 -03:00
diodiogod 5735616794 Prevent invalid hash seed from breaking isolated runtimes 2026-07-10 00:28:12 -03:00
diodiogod 102f114ae6 Standardize resolved voice prompt logging 2026-07-10 00:20:00 -03:00
diodiogod 4494381176 Finalize Fish Audio S2 engine integration 2026-07-09 23:13:24 -03:00
diodiogod 84e82b7d31 Refine Fish Audio S2 compile and override logging 2026-07-08 23:21:16 -03:00
diodiogod 984f0e9fa5 Fix VibeVoice native speaker mapping and logging 2026-07-07 00:56:57 -03:00
diodiogod 9081d3c22a Add Fish Audio S2 engine and fix VibeVoice speaker remap 2026-07-06 23:35:13 -03:00
diodiogod a41ac5d89e Merge origin/main into feature/combined-granite-echo-testing 2026-06-23 18:27:49 -03:00
diodiogod 99ea0bc6f9 Refine Granite ASR diarization docs and timestamp handling 2026-06-23 18:21:19 -03:00
diodiogod e6c607b582 Fix Granite diarization label formatting and SRT punctuation regressions 2026-06-23 18:04:44 -03:00
tazztone e7084f1bbc fix(granite-asr): resolve diarization multi-speaker turns and improve no-timestamp sequential timing 2026-06-23 11:29:39 +02:00
tazztone 8674797e7f feat: prefix diarized text with speaker IDs and update Granite adapter logic and ignore list 2026-06-23 10:54:28 +02:00
tazztone 0a8081f9c3 feat(granite): add speaker diarization for granite-speech-4.1-2b-plus and fix test runner environment detection 2026-06-23 10:30:04 +02:00
tazztone 3436dbdab2 feat(granite): integrate Granite 4.1 2B plus native timestamps, bypass Qwen aligner, fix is_plus undefined NameError and false warnings 2026-06-20 11:05:39 +02:00
tazztone 29515feb35 feat(granite,echo_tts): support granite-speech 4.1 ASR and implement echo-tts interrupt callbacks 2026-06-19 16:10:23 +02:00
diodiogod 3717fc0cbe Refine OmniVoice loading and progress logs 2026-06-18 22:57:12 -03:00
diodiogod af13209b47 Add OmniVoice engine with native SRT duration targeting 2026-06-18 22:23:32 -03:00