# rhasspy/piper

A fast, local neural text to speech system

Repository: https://github.com/rhasspy/piper
Canonical: https://ross.abutalabs.com/products/piper
Homepage: https://rhasspy.github.io/piper-samples/
Language: C++
License: MIT
License Family: permissive
Topics: speech-synthesis, text-to-speech, tts
Archived: true
Last push: 2025-08-26T15:01:29+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 38, release rhythm 8, longevity 95
- inputs: {"age_days": 1331, "days_push": 372, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11281, forks 1065 (observed 2026-08-28T04:10:46.648567+00:00)

## What it is
Piper is a fast, local neural text-to-speech system that runs offline on modest hardware, including Raspberry Pi devices. It offers many pre-trained voices at multiple quality levels, including multi-speaker models, and is now maintained in a successor repository (OHF-Voice/piper1-gpl).

## Use cases
- run text to speech offline on a raspberry pi
- generate speech audio from text locally without cloud
- add voice output to a home assistant
- convert text files to spoken audio
- use multi-speaker neural tts voices
- build a private voice assistant with local speech synthesis

## When to choose
- you need fast, private, offline text-to-speech on low-power hardware
- you want many pre-trained voices without training your own
- you are building a local voice assistant or embedded speech output

## When to avoid
- you need cloud-hosted, ultra-realistic studio-grade voices
- you want to train custom voices from scratch with full tooling
- you expect active development on this original repository rather than the successor piper1-gpl

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, speech-recognition, machine-learning, cli
- domain: speech-processing, machine-learning
- platform: cross-platform, python, cpp, cli, embedded
- tags: text-to-speech, neural-tts, local-inference, voice-models, offline, rhasspy, natural-language-processing

## Member repositories
- rhasspy/piper (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.648567+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:15:59.390473+00:00, confidence not recorded.
  - readme: https://github.com/rhasspy/piper (fetched 2026-08-28T04:10:46.648567+00:00, sha 468eb54e31be)
  - homepage: https://rhasspy.github.io/piper-samples/ (fetched 2026-08-29T08:14:39.455672+00:00, sha 7d76fba281ae)
- Data as of 2026-08-30T08:39:29.467469+00:00.