Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UI
Kokoro-FastAPI is a Dockerized FastAPI service that turns text into speech using the Kokoro-82M model through an OpenAI-compatible API. It is used by developers and self-hosters who need multilingual, multi-speaker speech generation, captions, phonemes, or an optional web interface.
Latest release v0.9.1 — v0.9.1: Security Bumps, IME & MPS Fixes · 28 Oct 2026
6 files for Claude Code, Codex and OpenCode: api-contrib, integration-tests, readme-benchmarks, web-contrib and 2 more — 927 tokens loaded in every session.
AGENTS.md A 927 tok .claude/skills/api-contrib/SKILL.md A 39 tok .claude/skills/integration-tests/SKILL.md A 25 tok .claude/skills/readme-benchmarks/SKILL.md A 52 tok .claude/skills/web-contrib/SKILL.md A 41 tok .claude/skills/adding-normalizer/SKILL.md A 44 tok These files are remsky/Kokoro-FastAPI's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.