kokoro-onnx
TTS with kokoro and onnx runtime
Decision gist · record as of 2026-08-14
Yes, if you need lightweight multilingual text-to-speech with ONNX inference. The low installation friction, active maintenance, and zero known vulnerabilities make it a practical choice. However, verify the unclear license treatment against your project's requirements, and plan for the separate download of model files before first use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires downloading model files (kokoro-v1.0.onnx and voices-v1.0.bin) separately and placing them in the working directory before first use.
- Low installation friction with a pure Python wheel and four runtime dependencies.
- Active maintenance with recent commits.
License · maintenance · safety
(unclear) — License treatment is unclear in the package metadata, though the description notes the package itself is MIT while the underlying Kokoro model uses Apache 2.0. Verify licensing terms before use in proprietary or restricted contexts.
last release 2026-01-30 (196 days) · last repo commit 2026-07-05 · 2,672 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 550,894 downloads/mo, #6,052 on PyPI
Alternatives
Verify before relying
pip install kokoro-onnx
from kokoro_onnx import Kokoro
kokoro = Kokoro(lang="en-us")
kokoro.create(text="Hello world", voice="af_heart", speed=1.0, outfile="audio.wav")- Whether the unclear license treatment poses practical restrictions for commercial or closed-source projects.
- Performance characteristics on hardware other than macOS M1 mentioned in the description.
- Whether all supported languages and voices are documented outside the external Hugging Face link.
- Exact size of downloaded model files in typical deployment scenarios.
What it is and what it does
Kokoro-onnx is a text-to-speech engine that runs inference using ONNX Runtime, wrapping the Kokoro-TTS model to generate speech from text. It supports multiple languages and offers a selection of voices, with model weights optimized for size while maintaining performance on modern hardware. The package depends on espeakng-loader for phoneme handling, numpy for numerical operations, onnxruntime for model inference, and phonemizer-fork for linguistic processing.
The typical workflow involves installing the package, downloading the model and voice files from the project's releases, then calling the Kokoro class with text, language, voice, and output parameters. It's designed for developers who need embedded speech synthesis without heavy dependencies like full TensorFlow or PyTorch installations, making it suitable for edge deployment or resource-constrained environments.
Use it for
- Generate speech for accessibility features in applications that need multiple language support.
- Create audio narration for content in real-time or batch processing pipelines.
- Build chatbot or voice assistant backends with lightweight inference on consumer hardware.
- Produce multilingual voiceovers for media or educational content with minimal model overhead.
- Prototype or deploy TTS features in resource-limited environments like embedded systems or edge devices.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need lightweight multilingual text-to-speech with ONNX inference.
The low installation friction, active maintenance, and zero known vulnerabilities make it a practical choice. However, verify the unclear license treatment against your project's requirements, and plan for the separate download of model files before first use.
Install
kokoro-onnx on PyPI
Before you install
Low installation friction with a pure Python wheel and four runtime dependencies. Active maintenance with recent commits.
Requires downloading model files (kokoro-v1.0.onnx and voices-v1.0.bin) separately and placing them in the working directory before first use.
License in practice
License treatment is unclear in the package metadata, though the description notes the package itself is MIT while the underlying Kokoro model uses Apache 2.0. Verify licensing terms before use in proprietary or restricted contexts.
Quickstart
pip install kokoro-onnx
from kokoro_onnx import Kokoro
kokoro = Kokoro(lang="en-us")
kokoro.create(text="Hello world", voice="af_heart", speed=1.0, outfile="audio.wav")Verify before relying
- Whether the unclear license treatment poses practical restrictions for commercial or closed-source projects.
- Performance characteristics on hardware other than macOS M1 mentioned in the description.
- Whether all supported languages and voices are documented outside the external Hugging Face link.
- Exact size of downloaded model files in typical deployment scenarios.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <3.14,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesespeakng-loadernumpyonnxruntimephonemizer-fork |
| Maintenance | Actively maintained 196 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 550,894 / month, #6,052 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: kokoro_onnx-0.5.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “text to speech onnx”
- kokoro-onnxConverts text to speech using ONNX Runtime, supporting multiple…
- sherpa-onnx-coresherpa-onnx-core provides pre-built ONNX runtime binaries for speech…
- onnx-asrAutomatic Speech Recognition using ONNX models with minimal…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also kokoro · piper-tts · pocket-tts · misaki · pyopenjtalk · TTS · pyttsx3 · coqui-tts · chatterbox-tts · nemo-text-processing