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

This project helps create natural-sounding spoken audio from written text in eight languages, including Japanese, English, and Chinese. You input text, select from hundreds of speaker voices, and receive high-quality audio files. It's ideal for content creators, educators, or anyone needing realistic voiceovers for multimedia.

Use this if you need to quickly generate lifelike voice narration in multiple languages for videos, presentations, or accessibility features, without hiring voice actors.

Not ideal if you require very specific vocal nuances or emotional expressions that go beyond standard text-to-speech capabilities, or if you only need a single, highly specialized voice.

voice-generation audio-content-creation e-learning multilingual-communication digital-publishing
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.