# thewh1teagle/kokoro-onnx

TTS with kokoro and onnx runtime

Repository: https://github.com/thewh1teagle/kokoro-onnx
Canonical: https://ross.abutalabs.com/products/kokoro-onnx
Homepage: https://pypi.org/project/kokoro-onnx
Language: Python
License: MIT
License Family: permissive
Topics: kokoro, onnxruntime, python, tts
Last push: 2026-08-19T17:08:56+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 40, longevity 43
- inputs: {"age_days": 607, "days_push": 14, "days_rel": 550, "gap_med": 28.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2680, forks 298 (observed 2026-08-28T04:07:10.005580+00:00)

## What it is
A Python library that runs the Kokoro text-to-speech model via ONNX Runtime, supporting CPU and GPU inference. It provides multi-language TTS with multiple voices in a lightweight package (~300MB, ~80MB quantized).

## Use cases
- convert text to speech audio in python
- generate wav files from text with kokoro tts
- run tts locally on cpu without heavy dependencies
- add voice narration to an app or pipeline
- use quantized tts model for low-resource devices
- synthesize speech in multiple languages with different voices

## When to choose
- you want fast, lightweight local TTS with ONNX Runtime
- you need CPU or GPU inference without PyTorch
- you want multiple voices and multi-language support
- you need a pip-installable TTS library with model files from GitHub releases

## When to avoid
- you need the highest-quality neural TTS from large models
- you need streaming real-time synthesis APIs not provided here
- you want cloud-hosted TTS with managed voices
- you need fine-grained voice cloning

## Facets
- artifact type: library
- maturity: active
- function: tts, machine-learning, llm-inference
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: text-to-speech, onnx-runtime, kokoro, speech-synthesis, lightweight-models, audio, cpu, gpu

## Member repositories
- thewh1teagle/kokoro-onnx (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.005580+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:17:56.938481+00:00, confidence not recorded.
  - readme: https://github.com/thewh1teagle/kokoro-onnx (fetched 2026-08-28T04:07:10.005580+00:00, sha 26c1abe64de5)
  - homepage: https://pypi.org/project/kokoro-onnx (fetched 2026-08-29T10:00:11.767438+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/kokoro-onnx/json (fetched 2026-08-29T10:00:11.776439+00:00, sha 840038395a9e)
- Data as of 2026-08-30T08:39:29.467469+00:00.