voicebox

mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-17 05:40:42 -07:00

Files

T

James Pine 70ca7f66cb feat: chunked TTS generation for long text (engine-agnostic)

Text exceeding max_chunk_chars (default 800) is automatically split at
sentence boundaries, generated per-chunk, and concatenated with a 50ms
crossfade.  Works with all engines (Qwen, LuxTTS, Chatterbox, Turbo).

- Abbreviation-aware sentence splitter (Dr., Mr., e.g., decimals)
- CJK sentence-ending punctuation support
- Paralinguistic tag preservation ([laugh], [cough], etc.)
- Per-chunk seed variation to avoid correlated RNG artefacts
- Per-chunk Chatterbox trim (catches hallucination at each boundary)
- max_chunk_chars exposed as per-request param on GenerationRequest
- Text max_length raised to 50,000 characters

Closes #99

2026-03-13 06:21:34 -07:00

__init__.py

Initialize voicebox project with backend, frontend, and Tauri setup. Added configuration files, dependencies, and basic structure for components, hooks, and utilities. Included README and setup documentation for guidance.

2026-01-25 02:19:06 -08:00

audio.py

fix: specify WAV format for atomic save temp file

2026-03-13 04:34:26 -07:00

cache.py

Implement profile cache management in audio processing

2026-01-30 16:50:24 -08:00

chunked_tts.py

feat: chunked TTS generation for long text (engine-agnostic)