aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2026-09-04fix: sglomni retry contract, booting detection, CLI keys, companion refresh, ↵historia
ffmpeg dep
2026-09-04refactor: share the HF cache helpers between qwen and sglomnihistoria
2026-09-04readme: uninstall sectionhistoria
2026-09-04rewrite backend documentationhistoria
2026-09-04readmehistoria
2026-09-03feat: pip install checks for bad crc errors and purges cache automaticallyhistoria
2026-09-03fix: increase gpu memory for MOSS with gplang-omni to .87historia
2026-09-03feat: gplang-omni reserves 70% of gpu 0 memory, preventing oom errors on ↵historia
consumer cards
2026-09-02fix: warn before using a likely too-big chunk size for sglang-omni modelshistoria
2026-09-02feat: reserve 20% vram when running higgs with sglang-omnihistoria
2026-09-02feat: add model and voice labels to generate audiobooks status tuihistoria
2026-09-02feat: move clone .wav directory to settingshistoria
2026-09-02fix: remove overlong text in config backend tuihistoria
2026-09-02feat: voice menu combined for tts/clone paths in tuihistoria
2026-09-02feat: sglang-omni model picker on manual server launchhistoria
2026-09-02rename generator to tts-audiobook-generator. remove pointless upgrade flashes.historia
2026-09-02fix: ZONOS2 only generating 1024 tokens maxhistoria
2026-09-02feat: auto-update via settingshistoria
2026-09-02feat: sglang backend supporthistoria
2026-09-01fix: server status for already-running serverhistoria
2026-09-01slop refactor/deduphistoria
2026-09-01fix: spec santizer for glm, outetts, miotts, minimax.historia
2026-09-01fix: hide speech-to-speech only models from config wizardhistoria
2026-09-01fix: better errors for generate all modelshistoria
2026-08-31feat: generate a book with all installed models to comparehistoria
2026-08-31fix: truncate excess spaces on generate audiobooks tuihistoria
2026-08-31feat: model capabilities lined up in tui menuhistoria
2026-08-30fix: non-clone models correctly supported in tui, restart server when neededhistoria
2026-08-30feat: output log path when audiobook generation failshistoria
2026-08-30fix: menu highlight numbering in tuihistoria
2026-08-29fix: crash on bad model_specs from audio.cpp, sanitizedhistoria
2026-08-29remove: pointless success flashes in tui for downloadshistoria
2026-08-28fix: no .wav directory error formattinghistoria
2026-08-28feat(audio.cpp): if github binary download fails, automatically start ↵historia
building from source
2026-08-28fix: better error when no .wav available to clonehistoria
2026-08-28feat: offer to download prebuilt mac/win binaries, new macos build fallback ↵historia
if xcode is not installed
2026-08-28feat: cli auto-starts and stops locally-managed servers if no --api-url is ↵historia
passed
2026-08-28feat: run auto-build audio.cpp scripts for macos and windowshistoria
2026-08-28refactor: overhaul config.py, remove cli default optionshistoria
2026-08-28fix: remove backtrace from console output when using incorrect/incomplete ↵historia
cli flags
2026-08-28fix: japanese characters not truncated correctly in tui terminal outputhistoria
2026-08-28feat: .wav hints for all voice directory pickers in tuihistoria
2026-08-28fix: system python used instead of venv python, breaking whisper transcriptionhistoria
2026-08-28remove: unnecessary flash on succesful buildhistoria
2026-08-28feat: unified logging with logging_kit.pyhistoria
2026-08-28feat: cuda arch detection for shorter builds, build failure detectionhistoria
2026-08-28feat: qwen-tts backend widgets updated to same style as audio.cpphistoria
2026-08-28fix: silently failing whisper transcriptionhistoria
2026-08-27remove: unnecessary tui texthistoria
2026-08-27fix: can't check checkboxes in tts model pagehistoria
generated by cgit v1.2.3 (git 2.25.1) at 2026-10-24 12:21:04 +0000