ayutaz/piper-plus

Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT) with VITS architecture. 571 speakers, prosody features, WavLM discriminator, multi-GPU training, WebAssembly, and FP16 ONNX export. Fork of Piper with enhanced Japanese support. Install: pip install piper-tts-plus

46
/ 100
Emerging

Based on the README, here's a technical summary that goes beyond the GitHub description: --- Implements VITS-based vocoder training with integrated phoneme-level prosody control through duration prediction and WavLM discriminator feedback during training. Supports real-time streaming synthesis via C++/Rust CLI with automatic speaker balancing across language groups and phoneme-level timing outputs. Targets multi-platform deployment across Python/C++/C#/Rust/Go/WebAssembly with unified model format (ONNX FP16), enabling browser-based inference without server dependencies or native integration via HTTP APIs and language-specific bindings.

No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

81

Forks

5

Language

C++

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ayutaz/piper-plus"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.