Text-to-speech Sourced statement

NeuTTS Air 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 useYes
Licenseapache-2.0
Stated memoryNot stated
Device memory8 GB RAM

Results

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

What the sources say about Pi 5

  • Model authors Quantisations in GGUF format 'ready to run on phones, laptops, or even Raspberry Pis' (vendor). source
    Caveat: No Pi speed figure published

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 NeuTTS Air

RuntimePrecisionDocumented devices
neutts (PyTorch)fp32CPU, GPUsource
neutts[llama] (GGUF via llama.cpp)Q4_0 / Q8 GGUFCPU, Metal, CUDA, ROCmsource
neutts[onnx]ONNXCPUsource

Run it

pip install "neutts[llama]"   # GGUF backbones via llama-cpp-python; see README for Metal/BLAS build flags

Copied from the linked README. We haven't run it on this device.

Caveats

  • 552M parameters is large for a Pi; expect slower than real time unless a source says otherwise
  • No Pi speed figure published

New open speech models: will they run on your hardware?

One email a week: new open TTS/STT models, license gotchas, and what we measured on CPUs, Macs, Pis and consumer GPUs.