Text-to-speech Sourced statement

Piper (voices) on Raspberry Pi 5

Benchmark pending. We haven't measured this pair yet. Below is what the sources say about this hardware, quoted with links.

Hobbyist single-board computer. Common for Home Assistant voice and offline assistants. Small models only.

EvidenceSourced statement

Commercial useConditional

LicenseVoices repo: MIT; engine (piper1-gpl): GPL-3.0

Stated memoryNot stated

Device memory8 GB RAM

Results

Benchmark pending. No measured numbers from us yet for Piper (voices) on Pi 5. Get notified or send us your numbers (with the method).

What the sources say about Pi 5

Third-party docs Home Assistant docs: Piper is 'optimized for the Raspberry Pi 4'; on a Raspberry Pi with medium-quality voices it generates 1.6 s of voice per second. source
Caveat: Refers to Raspberry Pi 4; a Pi 5 should be faster but we haven't measured it

Method

We haven't run this pair. Everything on this page is quoted from the linked sources, with the source type labelled (model authors vs third parties). Vendor numbers are often measured under favourable conditions.

Ways to run Piper (voices)

Runtime	Precision	Documented devices
piper-tts (onnxruntime	fp32 ONNX voices	CPU (optional --cuda)	source

Run it

pip install piper-tts
python -m piper.download_voices en_US-lessac-medium
python -m piper -m en_US-lessac-medium -f out.wav -- 'This is a test.'

We ran this exact command on our test box on 2026-10-21.

Caveats

Refers to Raspberry Pi 4; a Pi 5 should be faster but we haven't measured it