Commit Graph
29 Commits
Author SHA1 Message Date
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 97f4a0c365 Add unified MOSS audio generation workflows 2026-07-16 12:35:01 -03:00
diodiogod f81ebf1f9d Compact reference transcript documentation
Keep the Feature Comparison matrix concise by moving transcript mode explanations into a single footnote.
2026-07-13 22:05:04 -03:00
diodiogod 0c527ef541 Version 5.4.10
Document engine reference transcript requirements

Implementation details:
- Add typed reference_transcript metadata for every engine
- Extend the feature table generator for requirement-valued rows
- Regenerate the feature matrix with conditional mode notes
2026-07-13 21:35:59 -03:00
diodiogod 9757092aae Version 5.4.1
Address issue #311 with resilient MelBand resampling

Technical details:
- Route MelBand input conversion through the shared safe resampler.
- Fall back to torchaudio when librosa/Numba resampling is incompatible.
- Correct the PROJECT_INDEX path for bump instructions.
- Make version tooling use UTF-8 on Windows.
2026-07-10 14:06:12 -03:00
diodiogod 9081d3c22a Add Fish Audio S2 engine and fix VibeVoice speaker remap 2026-07-06 23:35:13 -03:00
diodiogod a0b58e42f7 Normalize large-language engine summaries in generated tables
- add full and compact language summary overrides to the engine table generator
- show Higgs Audio v3 with globe-style 100+ language summary in the README table
- show OmniVoice as 600+ languages in both compact and full generated tables
2026-06-23 12:10:00 -03:00
diodiogod 44d164c2b7 Fix OmniVoice language summary in generated tables
- add compact language summary override support to the table generator
- show OmniVoice as 600+ languages in the README summary table
- rename OmniVoice voice design feature text to instruction-based voice design
2026-06-23 12:06:07 -03:00
diodiogod ed0932d078 Trim README summary table isolation details 2026-06-14 10:17:30 -03:00
diodiogod afb35f5469 Summarize language counts in engine comparison 2026-06-11 08:00:28 -03:00
diodiogod b85067cc1c Treat RVC as language-agnostic in docs 2026-06-11 07:16:53 -03:00
diodiogod 4c0a0a934c Expand Higgs Audio v3 language coverage docs 2026-06-11 01:48:16 -03:00
diodiogod 8367bc12bf Sync isolation runtime documentation 2026-06-09 18:11:35 -03:00
diodiogod 2b61bafd73 Add shared VibeVoice isolation runtime 2026-06-06 15:09:27 -03:00
diodiogod f6ca9525a2 Refine generated training docs tables 2026-04-05 13:12:14 -03:00
diodiogod f1f05ae290 Document RVC training workflow and capabilities 2026-04-05 13:08:45 -03:00
diodiogod 6346122036 Generate README model auto-download table from YAML
- add README model download summary rows to the YAML source of truth
- generate and inject the README auto-download table via generate_engine_tables.py
- include Granite ASR in the generated model download summary
2026-03-17 00:19:02 -03:00
diodiogod c0e594ab43 Replace HTML comment markers in LICENSE with clean separator-based injection 2026-03-01 02:10:41 -03:00
diodiogod c834879563 docs: improve license table formatting for plain text rendering in LICENSE file 2026-03-01 02:06:04 -03:00
diodiogod 8849bcacfc docs: add model licenses to YAML source of truth, auto-generate license table in LICENSE file and full ENGINE_COMPARISON table 2026-03-01 02:02:30 -03:00
diodiogod bdf70c9954 docs: add engine count to quick comparison table title (auto-generated) 2026-03-01 01:40:34 -03:00
diodiogod 8f0c112da6 docs: split model sources and layouts from README 2026-02-20 13:46:00 -03:00
diodiogod acfe50980f docs: restore source of truth link in table generator
- Fix: Add source of truth note to generate_readme_condensed_table() in script
- Regen: README.md with permanent link
2026-02-11 23:46:27 -03:00
diodiogod 4e4c50045a docs: fix emoji encoding and update IndexTTS-2 size
- Fix: Insert Zero Width Non-Joiner between flag emojis in tables to prevent ligatures
- Update: Set IndexTTS-2 model size to ~4.7GB in YAML and Tables
2026-02-11 23:45:02 -03:00
diodiogod 2830dfc15f Update ASR docs and comparison tables
- add Qwen3 ASR feature info to README
- add ASR capability/feature to engine tables source
- add ASR column to engine comparison table
2026-02-05 00:26:08 -03:00
diodiogod 4f0782e75d Show all 10 engines in README comparison table
- Removed arbitrary filtering that only showed 7 engines
- Now displays complete engine list for informative overview
- Table remains condensed (4 columns) but comprehensive
2026-01-28 11:14:26 -03:00
diodiogod 28a738662e Clean up README condensed engine table
- Remove Speed column (unnecessary for overview)
- Remove 🎯 emoji from title (too many emojis)
- Add ChatterBox to featured engines (now shows 7 engines)
2026-01-28 11:10:29 -03:00
diodiogod ddadcdfec5 Add auto-generated condensed engine table to README and integrate with bump-version
- Enhanced table generator to create condensed 6-engine overview for README
- Auto-inject condensed table into README between HTML comment markers
- Added speed emojis (⚡⚡ Very Fast, ⚡ Fast, 🐌 Slow) for quick scanning
- Integrated table generation into bump-version script (runs on all bumps)
- Generator is idempotent: unchanged YAML = no git changes
- Usage: python scripts/generate_engine_tables.py --readme
- Table appears at top of README, right after project description
2026-01-28 11:06:44 -03:00
diodiogod 6c87d67ed7 Add YAML-driven engine documentation table generator
- 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"
2026-01-28 10:50:10 -03:00