Text-to-speech Measured by us
Kokoro 82M on CPU only (Intel N100 mini-PC / x86 desktop)
We ran it. Results below, with the exact hardware and settings.
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.
EvidenceMeasured by us
Commercial useYes
Licenseapache-2.0
Stated memoryNot stated
Device memory16 GB RAM
Results
| Runtime / settings | RTF | Time to first audio | Peak RAM | Load |
|---|---|---|---|---|
| kokoro-onnx fp32 (onnxruntime CPU) voice=af_heart | 0.1234 (8× real time) | 1.416 s | 933.9 MB | 1.11 s |
| kokoro-onnx int8 (onnxruntime CPU) voice=af_heart | 0.1480 (7× real time) | 1.686 s | 744.0 MB | 0.64 s |
Measured on Cloud x86 VM, 8 vCPU Intel Xeon, 16 GB RAM, no GPU (Intel(R) Xeon(R) Processor, 8 threads, Linux 6.12.94+, Python 3.13.5) on 2026-10-21. This is a cloud Xeon, not an N100: expect an N100 (4 cores, 6 W) to be several times slower. We'll post real N100 numbers when we have one.
Method
- Harness:
bench/run.py(open source), 5 timed runs after 1 warm-up, median reported. - Input: a fixed 2-sentence English passage (~10–11 s of audio). Time to first audio = first chunk from the streaming/sentence API.
- RTF = wall-clock processing time ÷ audio duration (lower is faster). Model load time is reported separately, not included.
- Peak RAM = whole-process RSS sampled every 20 ms, including model weights.
- Machine: Cloud x86 VM, 8 vCPU Intel Xeon, 16 GB RAM, no GPU. No other benchmark ran at the same time; a browser was open on the same VM.
Ways to run Kokoro 82M
Run it
pip install -U kokoro-onnx soundfile
curl -LO https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx
curl -LO https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.bin
python -c "from kokoro_onnx import Kokoro; import soundfile as sf; k=Kokoro('kokoro-v1.0.onnx','voices-v1.0.bin'); a,sr=k.create('Hello from Kokoro.', voice='af_heart', lang='en-us'); sf.write('out.wav', a, sr)"We ran this exact command on our test box on 2026-10-21.
Caveats
- Our CPU numbers come from an 8 vCPU cloud Xeon, which is several times faster than an Intel N100