marty1885/paroli
Streaming TTS based on Piper with optional RK3588 NPU support
Implements streaming speech synthesis via a split encoder-decoder architecture in C++, leveraging ONNX Runtime with optional hardware acceleration (CUDA, TensorRT, or RK3588 NPU for 4.3x speedup). Exposes functionality through both a CLI tool and a REST/WebSocket API server with authentication support, Opus compression, and a demo web UI.
123 stars.
Stars
123
Forks
26
Language
C++
License
MIT
Category
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.
Related tools
davidacm/NVDA-IBMTTS-Driver
This project is aimed at developing and maintaining the NVDA IBMTTS driver. IBMTTS is a...
IhorShevchuk/piper-app
The original Piper, now on iOS and macOS
ayutaz/piper-plus
Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT) with VITS architecture. 571 speakers,...
Elleo/pied
Pied makes it simple to install and manage text-to-speech Piper voices for use with Speech Dispatcher.
mush42/sonata-nvda
This add-on implements a speech synthesizer driver for NVDA using neural TTS models. It supports Piper