Leokani-tts 4.5M
Released November 5, 2026
- Parameters
- 4.3M
- Quantization
- FP32
- FP16
- INT8
- Format
- safetensors
- License
- Milliwatt Labs Model License
The same voice in a smaller model, for slower CPUs and microcontrollers. Just 4.3 million parameters.
Try it
Leokani-tts 7M
The full-size voice, with apps for Mac, iPhone, Android, Linux, Raspberry Pi and Home Assistant: Leokani-tts 7M.
Performance on one thread
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. — = not measured yet. | 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. — = not measured yet. | WER | UTMOS | ||
|---|---|---|---|---|---|---|---|---|---|
| Mac | 1 Arm core | Mac | 1 Arm core | ||||||
| Leokani-tts 4.5M PyTorch on one thread, like every row here. The ONNX version gives the same output, within 1 % of this speed on the Arm core. | 4.3M | 17 MB | — | 38× | — | 128 ms | 0.07 % | 3.56 | |
| Leokani-tts 7M | 7.0M | 28 MB | 90× | 27× | 50 ms | 181 ms | 0.07 % | 3.61 | |
| 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 |
|---|---|---|---|
| Linux | 1 Arm core (Cortex-A725, 2.8 GHz) | 38× | 128 ms |
| ESP32-P4 | ESP32-P4, 360 MHz, Arduino | 1.06× | 126 ms |
| ESP32-S3 | ESP32-S3, 240 MHz, Arduino | 0.56× | 247 ms |
| GPU | DGX Spark (GB10), many lines at once | 4,257× | 9 ms |
Download
hf download milliwattlabs/leokani-tts-4.5MSamples
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
Milliwatt Labs Model License: free for organizations with up to $1M in annual revenue. Training audio data generated from Kokoro-82M by hexgrad (Apache-2.0).
Commercial use needs a free registration. For a custom voice, email hello@milliwattlabs.com
Phonemes by Leokani G2P (MIT + CC BY 4.0): source, license.
Runs on ONNX Runtime Web (MIT).