zaakirio/kokoro-ru
text-to-speech model by zaakirio
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. Works with the stock kokoro package, unmodified. Russian TTS lives or dies on lexical stress — за́мок is a castle, замо́к is a padlock. rug2p.py resolves stress, ё and homographs with RUAccent, applies Russian vowel reduction, then phonemizes. Feed it text, not IPA. Whisper large-v3 round-trip against Piper, the incumbent free local Russian TTS, on identical sentences with identical ASR and normalisation. We average 2.50% WER against Piper's 4.38% and beat three of its four voices — but Piper's irina transcribes perfectly and we do not. Two caveats worth…
Read the full model card ↗ · Preview checked 2026-10-28T19:36:16.675Z
Inside the original model card — Document outline
- kokoro-ru
- Voices
- Usage
- Evaluation
- Limitations
- Training
- Acknowledgements
- ONNX / Node.js
- Python (onnxruntime)
- Node.js
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: openrail. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
zaakirio/kokoro-ru is a text-to-speech model repository published by zaakirio on Hugging Face. The source reports the kokoro library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- kokoro
- Recent downloads (30 days)
- 11,977
- Cumulative likes
- 10
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- openrail
- Access
- Not gated by Hugging Face
- Created
- 2026-07-29T19:27:33.000Z
- Last modified
- 2026-08-25T14:56:41.000Z
Compatibility and lineage
Reported languages: ru
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-25T06:37:43.686Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.