Kokoro TTS API

A self-hosted, OpenAI-compatible text-to-speech server built on Kokoro, with robust text processing and 28 voices. Plugs straight into the Read Aloud browser extension.

September 2025ShippedSource on GitHub ↗

A production-grade TTS server that speaks the OpenAI /v1 audio API, so any client that supports OpenAI TTS can point at it instead. It handles the unglamorous parts: cleaning and chunking messy input text, streaming audio, GPU acceleration when available, and exposing 28 Kokoro voices across US and UK English.

Built with accessibility as the goal: it works as a drop-in backend for the Read Aloud Chrome extension, giving free, local, natural-sounding read-aloud for any web page.

Hard parts

OpenAI-compatible API surface so existing clients work unchanged
Text normalisation and chunking for long, messy web pages

More work

Prep: voice coding copilotAn interview-prep IDE with a voice: a Monaco editor, a LeetCode-style problem library, and an AI copilot you can talk to, interrupt and point at your code.
Agent2DBA desktop database agent: connect PostgreSQL, ask in plain language, and let an agent explore the schema, write and run SQL, and remember what it learns, with a human approving every write.
voiceAgentA fully local, real-time voice assistant you can talk over: Parakeet listens, an LLM thinks, Kokoro speaks, SQLite remembers. Sub-second speech-to-speech with two-stage barge-in.