| Age | Commit message (Expand) | Author |
|---|
| 7 days | fix: spec santizer for glm, outetts, miotts, minimax. | historia |
| 7 days | fix: hide speech-to-speech only models from config wizard | historia |
| 7 days | fix: better errors for generate all models | historia |
| 8 days | feat: generate a book with all installed models to compare | historia |
| 8 days | fix: truncate excess spaces on generate audiobooks tui | historia |
| 8 days | feat: model capabilities lined up in tui menu | historia |
| 8 days | fix: non-clone models correctly supported in tui, restart server when needed | historia |
| 9 days | feat: output log path when audiobook generation fails | historia |
| 9 days | fix: menu highlight numbering in tui | historia |
| 10 days | fix: crash on bad model_specs from audio.cpp, sanitized | historia |
| 10 days | remove: pointless success flashes in tui for downloads | historia |
| 11 days | fix: no .wav directory error formatting | historia |
| 11 days | feat(audio.cpp): if github binary download fails, automatically start buildin... | historia |
| 11 days | feat: offer to download prebuilt mac/win binaries, new macos build fallback i... | historia |
| 11 days | feat: cli auto-starts and stops locally-managed servers if no --api-url is pa... | historia |
| 11 days | feat: run auto-build audio.cpp scripts for macos and windows | historia |
| 11 days | refactor: overhaul config.py, remove cli default options | historia |
| 11 days | fix: remove backtrace from console output when using incorrect/incomplete cli... | historia |
| 11 days | fix: japanese characters not truncated correctly in tui terminal output | historia |
| 11 days | feat: .wav hints for all voice directory pickers in tui | historia |
| 11 days | fix: system python used instead of venv python, breaking whisper transcription | historia |
| 11 days | feat: unified logging with logging_kit.py | historia |
| 11 days | feat: cuda arch detection for shorter builds, build failure detection | historia |
| 11 days | feat: qwen-tts backend widgets updated to same style as audio.cpp | historia |
| 11 days | fix: silently failing whisper transcription | historia |
| 11 days | fix: can't check checkboxes in tts model page | historia |
| 12 days | feat: nest start/stop server menu in configure backend menu | historia |
| 12 days | feat: flags for converting individual book files --input-book --output-book | historia |
| 12 days | feat: simply generate audiobooks menu, move more config to settings menu | historia |
| 12 days | fix: scrolling on help screen | historia |
| 12 days | feat: help menu in tui | historia |
| 12 days | feat: automatic updates added to configure backend menu | historia |
| 12 days | feat: better explanation of stop/exit setting | historia |
| 12 days | feat: menu for language options | historia |
| 12 days | feat: separate venvs for qwen-tts and faster, manage (un)installs | historia |
| 12 days | feat: manage qwen-tts model installs manually, delete model(s) when uninstalled | historia |
| 12 days | feat: design model support for qwen-tts backend. remove unnecessary port spli... | historia |
| 12 days | fix: settings menu only prompts to save after change | historia |
| 13 days | feat: language and option fields in tui, context-sensitive voice label | historia |
| 13 days | fix: crash when menu of clone voices is empty | historia |
| 13 days | feat: in-place toggle field, updated transcription tui to use new field | historia |
| 13 days | fix: default directory when choosing voices in tui | historia |
| 13 days | feat: combined install/configure tui screens into one menu, removed extraneou... | historia |
| 13 days | refactor: put shared ui screen code into ui.viewkit | historia |
| 13 days | refactor: audiocpp.py setup flow | historia |
| 13 days | refactor: split tts.py into per-backend packages | historia |
| 13 days | fix: broken venv imports | historia |
| 13 days | fix: stop remote form entries overwriting each other | historia |
| 13 days | fix(tts): honor quiet mode and drop request-level retries | historia |
| 13 days | refactor(audiocpp): pin checkout to app/audio.cpp, report install results | historia |
