Back to Gap Map Model components / Speech & audio

Piper

open source / Overall score: 3.0

A fast, local neural text-to-speech engine that embeds espeak-ng for phonemization, with a large catalog of downloadable voices and documented voice training. Its README lists Home Assistant and the NVDA screen reader among its users.

Maintained by the Open Home Foundation at OHF-Voice/piper1-gpl under GPL-3.0; the earlier rhasspy/piper repository, MIT-licensed, is archived.

Openness

5 high confidence

5.0

license: GPL-3.0(OSI)
source: public
core features withheld: no

Piper is GPL-3.0, an OSI-approved copyleft license, with no commercial edition; the published repository is the whole engine.

https://raw.githubusercontent.com/OHF-Voice/piper1-gpl/HEAD/COPYING recorded 2026-09-27
COPYING body: "GNU GENERAL PUBLIC LICENSE" "Version 3, 29 June 2007".
https://raw.githubusercontent.com/OHF-Voice/piper1-gpl/HEAD/README.md recorded 2026-09-27
README carries "A library from the Open Home Foundation" badge; the foundation maintains it ("The Open Home Foundation is looking for maintainers for Piper!") and it builds and trains from the repository.

Adoption

3 high confidence

3.0

PyPI downloads of piper-tts, the package the README installs. Downloads count installs, not voices synthesized.

https://pypistats.org/api/packages/piper-tts/recent recorded 2026-09-27
"last_month":893727 for piper-tts.

Capability

3 medium confidence

3.0

A complete local synthesizer with training support, but for one task and its own voice family.

https://raw.githubusercontent.com/OHF-Voice/piper1-gpl/HEAD/README.md recorded 2026-09-27
"A fast and local neural text-to-speech engine that embeds [espeak-ng][] for phonemization."; links "[Training new voices][training]".

Verified 2026-09-27