Compare software

Kokoro-FastAPI vs Cartesia: catalog facts
Kokoro-FastAPI	Cartesia
Best for: Self-hosting a fast text-to-speech back end for apps, readers or Home Assistant	Best for: Developers building real-time voice agents and speech features
Free Free and open source under the Apache 2.0 licence.	Paid Plans are listed on the pricing page, with a sales contact for larger deployments.
macOS, Linux, Self-hosted	Web
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	One API covers text-to-speech, transcription and voice agents Built for low-latency, real-time conversation All 3 strengths for Cartesia One API covers text-to-speech, transcription and voice agents Built for low-latency, real-time conversation Documentation for developers is published
AMD GPU support is experimental Apple Silicon has no prebuilt image	Mainly an API for developers rather than a consumer app Cloud only, with no local option All 3 limitations for Cartesia Mainly an API for developers rather than a consumer app Cloud only, with no local option Larger deployments go through sales
Self-hosted	Hosted service
Open source	Not open source
License: Apache-2.0	License not stated
No account needed	Account needed
Not stated if it works offline	Needs internet
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 Cartesia cartesia.ai Catalog checked September 26, 2026

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