Compare software

Kokoro-FastAPI vs Speaches: catalog facts
Kokoro-FastAPI	Speaches
Best for: Self-hosting a fast text-to-speech back end for apps, readers or Home Assistant	Best for: Developers who want local speech-to-text and text-to-speech behind an OpenAI-style API
Free Free and open source under the Apache 2.0 licence.	Free Free and open source under the MIT licence.
macOS, Linux, Self-hosted	Self-hosted
OpenAI-compatible speech endpoint Prebuilt multi-architecture Docker images with models included All 4 strengths for Kokoro-FastAPI OpenAI-compatible speech endpoint Prebuilt multi-architecture Docker images with models included Caption timestamps and phoneme endpoints Voice mixing and SSML support	Drop-in replacement for OpenAI's speech and transcription endpoints Streaming transcription over SSE All 4 strengths for Speaches Drop-in replacement for OpenAI's speech and transcription endpoints Streaming transcription over SSE Loads and unloads models automatically on demand Kokoro and Piper voices for text-to-speech
AMD GPU support is experimental Apple Silicon has no prebuilt image	A server with an API, not an end-user app Setup is based on Docker
Self-hosted	Self-hosted
Open source	Open source
License: Apache-2.0	License: MIT
No account needed	No account needed
Not stated if it works offline	Not stated if it works offline
Official website Full listing and sources Sources for Kokoro-FastAPI github.com/remsky/Kokoro-FastAPI Catalog checked September 26, 2026	Official website Full listing and sources Sources for Speaches speaches.ai github.com/speaches-ai/speaches Catalog checked September 26, 2026

“Not stated” means we have not confirmed it. Features can vary by device and plan.