Compare software

Kokoro-FastAPI vs Pocket TTS: catalog facts
Kokoro-FastAPI	Pocket TTS
Best for: Self-hosting a fast text-to-speech back end for apps, readers or Home Assistant	Best for: Developers and users who want CPU based text-to-speech
Free Free and open source under the Apache 2.0 licence.	Free Free and open source under the MIT license.
macOS, Linux, Self-hosted	Web, Command line
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	Runs on CPU without a GPU Offers both Python and command line interfaces All 4 strengths for Pocket TTS Runs on CPU without a GPU Offers both Python and command line interfaces Supports streaming audio and voice cloning Can be tried in a browser
AMD GPU support is experimental Apple Silicon has no prebuilt image	Requires Python 3.10 or later and PyTorch 2.5 or later.
Self-hosted	Downloadable app, Web application
Open source	Open source
License: Apache-2.0	License: MIT
No account needed	Not stated if an account is 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 Pocket TTS github.com/kyutai-labs/pocket-tts Catalog checked October 8, 2026

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