KO

Kokoro

Compact, high-quality open text-to-speech model

Self-Hosted AI ★ 9.3k stars Medium setup Apache-2.0

Kokoro is an open-weight text-to-speech model with a small parameter count that produces natural-sounding speech. It can be self-hosted with an OpenAI-compatible API wrapper for local speech synthesis.

Key features

  • Small high-quality model
  • Multiple voice presets
  • Low resource usage
  • Runs offline

Strengths

  • Released under the Apache-2.0 license
  • First-class Docker support for quick deployment
  • Mature project with 9.3k GitHub stars
  • Written in JavaScript

Is Kokoro secure?

OSV.dev has no published security advisories for Kokoro's repository. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

Source: OSV.dev, checked 2026-10-14. How this is measured.

Kokoro replaces

Health badge

Maintain Kokoro? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 42 · fair

Markdown
[![SelfHostIndex health score for Kokoro](https://selfhostindex.com/badge/kokoro-tts.svg)](https://selfhostindex.com/app/kokoro-tts/)
HTML
<a href="https://selfhostindex.com/app/kokoro-tts/"><img src="https://selfhostindex.com/badge/kokoro-tts.svg" alt="SelfHostIndex health score for Kokoro"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/kokoro-tts.svg
   :alt: SelfHostIndex health score for Kokoro
   :target: https://selfhostindex.com/app/kokoro-tts/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare Kokoro

8 head-to-head comparisons.

Similar self-hosted ai apps