root e0dec05885 fix: chunk large chapter text for Kokoro TTS to prevent EOF on big inputs ...

Split chapter text into ~1000-char sentence-boundary chunks before sending
to kokoro-fastapi. Each chunk is generated individually and the raw MP3 bytes
are concatenated. This prevents the EOF / timeout failures that occur when
the server receives a very large single request (e.g. a full PDF 'Full Text'
chapter). chunkText() breaks at sentence endings (. ! ? newlines) to preserve
natural speech flow.

2026-04-10 09:24:37 +05:00

..

cmd

feat(import): move PDF parsing to backend; fix heartbeat/reap for import_tasks

2026-04-09 21:19:43 +05:00

internal

fix: chunk large chapter text for Kokoro TTS to prevent EOF on big inputs

2026-04-10 09:24:37 +05:00

.dockerignore

feat: add v2 stack (backend, runner, ui-v2) with release workflow

2026-03-15 19:32:40 +05:00

Dockerfile

fix(backend): add ffmpeg to backend image for pocket-tts voice sample generation

2026-03-28 21:24:59 +05:00

go.mod

fix(pdf): replace dslipak/pdf with pdfcpu bookmark+content-stream extraction

2026-04-09 22:36:58 +05:00

go.sum

fix(pdf): replace dslipak/pdf with pdfcpu bookmark+content-stream extraction

2026-04-09 22:36:58 +05:00

todos.md

feat: add v2 stack (backend, runner, ui-v2) with release workflow

2026-03-15 19:32:40 +05:00