joungmin 20210830cf Fix TTS: switch to 1.7B with ref_audio, speakable text on all lines ...

- Use 1.7B model (0.6B had tensor mismatch with cached prompts)
- Speak endpoint uses ref_audio directly (not cached pkl) as fallback
- Cache voice clone prompts in memory on startup
- Add SpeakableText component: 🔊 icon on each p and li element
- Remove old TTSReader sequential approach
- Add global exception handler to TTS server
- Fix profile localStorage caching
- inference_mode + bf16 optimization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-13 12:14:06 +00:00

..

src

Fix TTS: switch to 1.7B with ref_audio, speakable text on all lines

2026-04-13 12:14:06 +00:00

build.sh

Add knowledge structuring feature with incremental LLM processing

2026-04-09 19:43:21 +00:00

eslint.config.mjs

Add backend/frontend scaffolding with Oracle ADB wallet config

2026-03-30 06:56:26 +00:00

next-env.d.ts

Implement all core features: Knowledge pipeline, RAG chat, Todos, Habits, Study Cards, Tags, Dashboard

2026-03-30 21:43:51 +00:00

next.config.ts

Add backend/frontend scaffolding with Oracle ADB wallet config

2026-03-30 06:56:26 +00:00

package-lock.json

Add English level settings, improve content structuring and rendering

2026-04-12 23:48:38 +00:00

package.json

Add English level settings, improve content structuring and rendering

2026-04-12 23:48:38 +00:00

postcss.config.mjs

Add backend/frontend scaffolding with Oracle ADB wallet config

2026-03-30 06:56:26 +00:00

tsconfig.json

Add backend/frontend scaffolding with Oracle ADB wallet config

2026-03-30 06:56:26 +00:00