Text-to-Speech Web UI screenshot
GitHub Project Updated May 2025

Text-to-Speech Web UI (Piper TTS)

Convert text to natural speech with Piper TTS

Text-to-Speech Web UI is a Streamlit application powered by Piper TTS, a fast and lightweight speech synthesis system. Convert text into natural-sounding speech with multiple generation modes: single voice, all voices, mixed voices per sentence, or with gaps between sentences. Supports all Piper TTS voice models. Place .onnx model files in C:/piper/models/ to use custom voices. Intended for personal, non-commercial use.

View on GitHub ↗

✦ Key Features

  • Multiple voice options—use any Piper TTS voice model
  • Multiple generation modes—single voice, all voices, mixed per sentence, or with gaps
  • Fast, lightweight Piper TTS—minimal latency
  • Streamlit web interface—easy to run locally
  • Supports custom voice models—place .onnx files in models directory

⌘ Technologies

PythonStreamlitPiper TTSNumPySciPy