Piper
Fast, small, local text-to-speech that runs on a Raspberry Pi. Not a voice cloner — a reliable speaking voice.
- Self-hosted
- Active
- Allowed adult content
- Open source
At a glance
- Where it runs
- Self-hostedYou run it on your own machine. Nothing leaves it unless you send it.
- Adult content
- AllowedAdult content is permitted within the published rules.
- Trains on your content
- NoYour content is not used to train models.
- Status
- ActiveMaintained and working today.
- Account needed
- No
- Licence
- GPL-3.0
- Cost
- Free and open source.
- What it keeps
- Local only.
What it takes to run
- Graphics memory
- No GPU needed
- System memory
- 2 GB, 4 GB recommended
- Disk
- about 2 GB
- Runs on
- Linux, macOS, Windows
Find what fits your machine on the tools page — pick your hardware from the first menu.
Piper does one thing: turn text into speech, quickly, offline, on very modest hardware. It is what the open-source home-assistant world uses, and the voices are pre-trained and permissively distributed rather than cloned from someone.
If what you need is narration rather than impersonation, this is the boring correct answer.
Worth knowing before you start
- Fixed voices It speaks in the voices that exist; cloning a new one is a training job, not a feature.
- Less expressive than the hosted services Clear and natural, but flatter than ElevenLabs.
What it does
- Runs on a Raspberry Pi
- Many pre-trained voices and languages
- No GPU needed
- Very fast
Signs of life
Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.
- Last answered
- Yes, 3 hours ago Its website responded when we asked.
- Stars on GitHub
- 5,591 539 forks.
- Last commit
- 9 hours ago2026-09-15 20:43 UTC
- Latest release
- v1.8.0
- Archived copy
- Wayback Machine A snapshot, in case this one stops answering.
Categories
Something here wrong or out of date? Tell us — this page is only worth having if it is right.