Leokani-tts
Released October 29, 2026
- Parameters
- 7M
- Quantization
- FP32
- FP16
- INT8
- Format
- safetensors
- License
- CC-BY-NC-4.0
Frontier-quality speech on any CPU, no GPU needed.
Try it
Performance
That sounds like a great plan! Let me know how it goes, and good luck tomorrow.
| Listen | Model | Params | Size | Speed (× real time) Mac: Apple M3 Pro CPU · 1 Arm core: Cortex-A725, 2.8 GHz The Mac columns run every model in Python/ONNX, like for like. Speed = seconds of speech per second of compute; first speech = median time to first audio over 20 sentences. Mac: M3 Pro CPU; Arm: one 2.8 GHz Cortex-A725 core (Raspberry Pi-class). WER (Whisper large-v3), UTMOSv2: 120 sentences. | First speech Mac: Apple M3 Pro CPU · 1 Arm core: Cortex-A725, 2.8 GHz The Mac columns run every model in Python/ONNX, like for like. Speed = seconds of speech per second of compute; first speech = median time to first audio over 20 sentences. Mac: M3 Pro CPU; Arm: one 2.8 GHz Cortex-A725 core (Raspberry Pi-class). WER (Whisper large-v3), UTMOSv2: 120 sentences. | WER | UTMOS | ||
|---|---|---|---|---|---|---|---|---|---|
| Mac | 1 Arm core | Mac | 1 Arm core | ||||||
| Leokani-tts PyTorch. The ONNX version gives the same output, within 1 % of this speed on the Arm core and 4 % on the Mac. | 7.0M | 28 MB | 90× | 25× | 50 ms | 190 ms | 0.07 % | 3.53 | |
| KittenTTS nano 0.8 | 14.0M | 60 MB | 26× | 3.6× | 240 ms | 1.7 s | 0.41 % | 2.18 | |
| Piper (en_US lessac medium) | 15.7M | 63 MB | 49× | 5.6× | 86 ms | 710 ms | 0.90 % | 3.77 | |
| KittenTTS mini 0.8 | 73M | 82 MB | 16× | 3.4× | 330 ms | 1.6 s | 0.21 % | 2.04 | |
| Kokoro-82M | 82M | 328 MB | 7.6× | 0.48× | 670 ms | 11 s | 0.35 % | 3.76 | |
| Kyutai Pocket TTS | 110M | 226 MB | 9.7× | 1.2× | 34 ms | 280 ms | 0.35 % | 3.25 | |
| Chatterbox | 798M | 3.2 GB | 0.28× | 0.028× | 15 s | 150 s | 0.55 % | 3.36 | |
Leokani on every platform
| Platform | Device | Speed | First speech |
|---|---|---|---|
| Mac Native app (Core ML), 20 lines, warm; voice loads in about 50 ms. | M3 Pro (native app) | 296× | 19 ms |
| iPhone Leokani 1.1, Core ML on the Neural Engine: the 8 sample lines at 101× real time, 64 ms per line (median, the whole line). Kokoro-82M on the same phone takes 308 ms to its first audio chunk (median). | 17 Pro Max | 101× | 64 ms per line |
| Browser | Chrome on Mac | 97× | 64 ms |
| Linux server | 1 vCPU VPS | 36× | 91 ms |
| Android | moto g play 2024 | 20.6× | 234 ms |
| Raspberry Pi | CM4, 4 cores | 11.5× | 0.44 s |
| ESP32-P4 | Coming soon | ||
| Windows | Coming soon | ||
Download
hf download milliwattlabs/leokani-ttsDownloads
-
Mac
Apple silicon · macOS 15+
21.9 MBDownload -
Mac command line
Apple silicon · macOS 15+
Unzip, then ./install.sh
20.2 MBDownload -
Linux
x86_64 · glibc 2.28+
tar xf, then ./install.sh
38.5 MBDownload -
Raspberry Pi
ARM64 Linux · Pi 3 or later
tar xf, then ./install.sh
37.3 MBDownload -
Android
Android 9+
Allow installs from this source
44.4 MBDownload -
JavaScript
Browsers & Node 20+
npm i ./leokani-1.1.0.tgz
4.5 MBDownload -
Home Assistant & Docker
x86_64 · Wyoming · OpenAI speech API
docker load -i, then docker run
138.2 MBDownload -
Home Assistant & Docker on ARM
ARM64 · Wyoming · OpenAI speech API
docker load -i, then docker run
133.9 MBDownload -
ESP32-P4
32 MB PSRAM
-
Windows
x64 · ARM64
Samples
Hello! I'm a small text-to-speech model, and I run on an ordinary computer.
That sounds like a great plan! Let me know how it goes, and good luck tomorrow.
Did you remember to water the tomatoes before the rain started?
Your flight leaves on March 14th at 7:45 AM, and the fare is 219 dollars.
The trail is 4.2 miles long, climbs about 1,200 feet, and takes around 3 hours.
Maria Gonzalez and Hiroshi Tanaka are meeting Dr. Okafor in Minneapolis on Friday.
The old lighthouse stood at the edge of the bay for more than a century, and every evening the keeper climbed one hundred and twelve steps to light the lamp.
Sure, no problem.
License
CC BY-NC 4.0, non-commercial use only. Training audio data generated from Kokoro-82M by hexgrad (Apache-2.0).
For a commercial license or a custom voice, email hello@milliwattlabs.com
Phonemes by espeak-ng (GPL-3.0): source, license.
Runs on ONNX Runtime Web (MIT).