# Piper

> Piper is a fast local text-to-speech engine that runs VITS voices exported to ONNX, with a CLI, web server, Python and C/C++ APIs. Development moved from the archived rhasspy/piper (MIT) to OHF-Voice/piper1-gpl, which is GPL-3.0. Voice licences vary by voice and the docs call Piper intended for personal use and research, so check each voice's MODEL\_CARD. It has no voice cloning (you can train new voices) and no speech recognition.

- Repository: https://github.com/OHF-Voice/piper1-gpl
- Official docs: https://github.com/OHF-Voice/piper1-gpl#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech generation (partial). Speech generation with preset downloadable voices; custom voices need training, no zero-shot cloning.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, fully local on CPU, optional CUDA GPU | https://github.com/OHF-Voice/piper1-gpl#readme | 2026-10-15 |
| Code licence | Partial | GPL-3.0 (copyleft; PyPI package declares GPL-3.0-or-later); the archived predecessor rhasspy/piper was MIT | https://github.com/OHF-Voice/piper1-gpl/blob/main/COPYING | 2026-10-15 |
| Model weights licence | Partial | Varies per voice; voices repo is tagged MIT but each voice's MODEL\_CARD lists its own dataset licence, some restrictive | https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/VOICES.md | 2026-10-15 |
| Commercial use | Partial | Possible with conditions; GPL-3.0 code and per-voice licences must be checked | https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/VOICES.md | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/OHF-Voice/piper1-gpl#readme | 2026-10-15 |
| Hardware | Partial | Runs on CPU via onnxruntime, optional CUDA; older prebuilt binaries target Raspberry Pi 3/4; no RAM numbers stated | https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/CLI.md | 2026-10-15 |
| Operating systems | Confirmed | PyPI wheels for Windows x64, macOS (Intel and Apple Silicon) and Linux (x86\_64 and aarch64) | https://pypi.org/project/piper-tts/#files | 2026-10-15 |
| Setup effort | Confirmed | Easy, pip install piper-tts then download a voice | https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/CLI.md | 2026-10-15 |

GitHub: 5889 stars, 570 forks, last push 2026-10-15, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/piper). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.