# Piper — card for AI agents

Fast local TTS engine (GPL-3.0) with downloadable voices under per-voice licenses.

Category: Voiceover (text-to-speech) · maker Open Home Foundation · checked 2026-10-10

## Price
- Price: Free
- Free tier: Self-hosted; compute only (fast on CPU).

## License
GPL-3.0 (engine); per-voice model licenses — https://github.com/OHF-Voice/piper1-gpl

- commercial: **conditions** (Commercial use with conditions)
  > Some voices may have restrictive licenses
  (https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/VOICES.md)
- attribution: **varies** (Credit depends on the item)
- in app: **conditions** (Ship inside your app with conditions)
- youtube: **conditions** (Monetized YouTube with conditions)

## Rules to follow
- Meet GPL-3.0 obligations if you distribute the engine with your app.
- Check each voice model's license and dataset terms.

## How an agent gets files
- pip install piper-tts; python3 -m piper.download_voices en_US-lessac-medium. HTTP server: pip install piper-tts[http], python3 -m piper.http_server -m en_US-lessac-medium, then POST /synthesize with JSON {"text": ...} (port 5000). (sign-in: none)
- Formats: wav, onnx
- Not allowed: Engine is GPL-3.0.
- Not allowed: Each voice has a MODEL_CARD file with its license; some voices have restrictive licenses.
- Not allowed: A voice needs a .onnx file and a .onnx.json file.

## How to connect
- Package (npm/PyPI)
- API docs: https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/API_HTTP.md
- PyPI: `pip install piper-tts`
- Repository: https://github.com/OHF-Voice/piper1-gpl
- Website: https://github.com/OHF-Voice/piper1-gpl

## Notes
The old rhasspy/piper (MIT) is archived. No zero-shot cloning. The README says the foundation is looking for maintainers.

## Numbers (AgentGid data)
- Gid Score: 45.5
- GitHub stars: 5,936
- Downloads last week: 501,637
- Used in 1 public projects set up for AI coding agents

## Lines to paste into your prompt or AGENTS.md

```
- Piper (Voiceover (text-to-speech)). Fast local TTS engine (GPL-3.0) with downloadable voices under per-voice licenses. Price: free; commercial use with conditions; credit depends on the item; ship inside your app with conditions.
  Connect: PyPI piper-tts.
  Get files: pip install piper-tts; python3 -m piper.download_voices en_US-lessac-medium. HTTP server: pip install piper-tts[http], python3 -m piper.http_server -m en_US-lessac-medium, then POST /synthesize with JSON {"text": ..} (port 5000) (wav, onnx).
  Not allowed: Engine is GPL-3.0.
  Not allowed: Each voice has a MODEL_CARD file with its license; some voices have restrictive licenses.
  Not allowed: A voice needs a .onnx file and a .onnx.json file.
  Rule: Meet GPL-3.0 obligations if you distribute the engine with your app.
  Rule: Check each voice model's license and dataset terms.
  License: https://github.com/OHF-Voice/piper1-gpl (checked 2026-10-10; details: https://agentgid.com/assets/piper/)
```

Not verified: Per-voice dataset terms not checked (the HF card says MIT).

## Links
- AgentGid page: https://agentgid.com/assets/piper/
- Is it free for commercial use? https://agentgid.com/assets/piper/commercial-use/
- Source: https://github.com/OHF-Voice/piper1-gpl
- Source: https://github.com/rhasspy/piper
- Source: https://huggingface.co/rhasspy/piper-voices

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.