selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

zaakirio logo

kokoro-ru

zaakirio·released 29 Jul 2026

OpenRAIL82M≈0.7 GB
Runs on CPU or any GPU≈156 MB of weights
hf download zaakirio/kokoro-ru
Setup ↓

Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.

How much VRAM does kokoro-ru need?

At FP16 / BF16 kokoro-ru needs about 0.7 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use0.1 GB ≈0.6 GB
8-bitLossless in practice, twice the size of Q40.1 GB ≈0.6 GB
FP16 / BF16recommendedFull precision, as released0.1 GB ≈0.7 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it.

Can the RTX 4060 run kokoro-ru? →

Run kokoro-ru locally

About kokoro-ru

Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors. A Russian port of Kokoro-82M. Sveta — heard in the clip above — is the flagship voice. She and Masha share one checkpoint and differ only by voicepack, so the release is two model files, not three.

Full model card on Hugging Face →

Alternatives to kokoro-ru

All alternatives →
hexgrad logo

Kokoro-82M

hexgrad·TTS

≈0.7 GB

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.

82MApache 2.0
13.3MDec 2024gguf
KittenML logo

kitten-tts-2-mini

KittenML·TTS

≈0.7 GB

82M parameters, 16 languages, 118 voices, 24 kHz. ONNX with int8 weights (82.7 MB; runs on CPU, no PyTorch needed), and the float32 PyTorch weights.

82MApache 2.0
8.4KNov 2026
OpenMOSS-Team logo

MOSS-TTS-Nano-100M

OpenMOSS-Team·TTS

≈0.7 GB

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving…

100M32K ctx Apache 2.0
122.1KApr 2026gguf
hexgrad logo

Kokoro-82M-v1.1-zh

hexgrad·TTS

≈0.7 GB

Kokoro is an open-weight series of small but powerful TTS models.

82MApache 2.0
85.6KFeb 2025gguf
Oomni logo

mithi-v1-flash

Oomni·TTS

≈0.7 GB

A small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female).

99MApache 2.0
1.5KNov 2026
Supertone logo

supertonic-2

Supertone·TTS

≈0.7 GB

Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

66MOpenRAIL
5.5KJan 2026gguf

kokoro-ru FAQ

How much VRAM does kokoro-ru need?
About 0.7 GB at FP16 / BF16.
Can kokoro-ru run on the RTX 4060?
Yes. It fits at FP16 / BF16 (about 0.7 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use kokoro-ru commercially?
Yes, with conditions. It is released under OpenRAIL. Commercial use allowed, but with use-based restrictions that pass on to derivatives.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.