Text-to-speech Sourced statement

Pocket TTS on CPU only (Intel N100 mini-PC / x86 desktop)

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

No GPU. Covers low-power N100 boxes up to desktop CPUs. Our own CPU numbers come from an 8 vCPU cloud Xeon, which is faster than an N100.

EvidenceSourced statement
Commercial useYes
Licensecc-by-4.0
Stated memoryNot stated
Device memory16 GB RAM

Results

Benchmark pending. No measured numbers from us yet for Pocket TTS on CPU only. Get notified or send us your numbers (with the method).

What the sources say about CPU only

  • Model authors Runs on CPU using only 2 cores; ~200 ms to first audio chunk (vendor). source
  • Model authors On a cloud VM with 4 vCPUs, the README reports ~2.3–2.5x real time on CPU. source

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 Pocket TTS

RuntimePrecisionDocumented devices
pocket-tts (PyTorchfp32, int8 dynamic quant (CPU only)CPU (GPU optional)source
sherpa-onnx (third-party)ONNXWindows/macOS/Linux, Raspberry Pi, Jetson, RK3588source
MLX port (communityMLXApple Siliconsource

Run it

pip install pocket-tts      # Linux: add --extra-index-url https://download.pytorch.org/whl/cpu to skip CUDA wheels
pocket-tts generate

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

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.