Piper is a fast, local neural text-to-speech (TTS) system developed by the Rhasspy team. Optimized for devices like the Raspberry Pi 4, Piper enables high-quality speech synthesis without relying on cloud services, making it ideal for privacy-conscious applications. It utilizes ONNX models trained with VITS to deliver natural-sounding voices across various languages and accents. Piper is particularly suited for offline voice assistants and embedded systems.

Features

  • Local neural TTS engine optimized for Raspberry Pi 4
  • Supports multiple languages and accents with downloadable voice models
  • Utilizes ONNX models trained with VITS for high-quality synthesis
  • Offers varying quality levels from x_low to high (16kHz to 22.05kHz)
  • Compatible with Rhasspy and other voice assistant platforms
  • Open-source under the MIT license

Project Samples

Piper TTS Screenshot 1

Project Activity

See All Activity >