marty1885/paroli

Streaming TTS based on Piper with optional RK3588 NPU support

56
/ 100
Established

This tool helps convert written text into natural-sounding speech in real-time. You provide text, and it generates audio output, like a spoken narration. It's designed for developers building applications that need to add text-to-speech capabilities, such as virtual assistants, accessibility tools, or interactive voice response systems.

123 stars.

Use this if you are a developer integrating streaming text-to-speech into an application and need a performant C++ solution, optionally leveraging hardware accelerators like NVIDIA GPUs or Rockchip NPUs.

Not ideal if you are an end-user simply looking for a ready-to-use desktop text-to-speech application or a service that doesn't require technical setup.

voice-user-interface speech-synthesis application-development embedded-systems AI-powered-apps
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

123

Forks

26

Language

C++

License

MIT

Last pushed

Feb 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/marty1885/paroli"

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