jpreprocess/jbonsai
Voice synthesis library for Text-to-Speech applications (Currently HTS Engine rewrite in Rust language)
Converts full-context linguistic labels into PCM audio waveforms using statistical parametric synthesis models (.htsvoice format). Built in Rust with design priorities for readability, performance, and low memory footprint while maintaining WebAssembly compatibility. Currently targets Japanese synthesis via the HTS Engine architecture, accepting pre-computed phonetic feature sequences for deterministic voice generation.
Stars
13
Forks
4
Language
Rust
License
BSD-3-Clause
Category
Last pushed
Mar 18, 2026
Monthly downloads
41
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jpreprocess/jbonsai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jpreprocess/jpreprocess
Japanese text preprocessor for Text-to-Speech applications (OpenJTalk rewrite in rust language)
isomoes/blivedm_rs
一个功能强大的 Bilibili 直播间弹幕 WebSocket 客户端 Rust 库，支持实时弹幕监控、文字转语音（TTS）和浏览器 Cookie 自动检测。A powerful...
CodersCreative/natural-tts
A rust crate for easily implementing Text-To-Speech into your rust programs.
thewh1teagle/piper-rs
Use piper TTS models in Rust
TrevorS/qwen3-tts-rs
Rust implementation of Qwen3-TTS speech synthesis