SpeakshelfTEXT TO SPEECH CATALOG
4,753 voices. One shelf.
Speakshelf catalogs the text to speech voices of Google Cloud, Amazon Polly, Kokoro and more. Each with a sample you can play in the browser. No account, no setup, just the voices.
3 providers
Every provider keeps a full shelf: the complete voice list with filters and playback, notes on each model family, and a page per language. The shelf grows: the AI TTS Microservice unifies more providers, and new shelves open here once verified.
Why one shelf
Catalogs differ in more than size. Keeping them side by side shows the gaps, the overlaps and the character of each.
Coverage adds up
Amazon Polly brings Welsh, which Google Cloud doesn't carry at all, plus regional variants like Arabic (Standard) and Arabic (United Arab Emirates). One shelf shows what each provider has that the others lack.
One way to listen
Same filters, same player, same voice id scheme on every shelf. Comparing voices across providers is two clicks, not two consoles.
Fresh on its own
Every shelf refreshes from the AI TTS Microservice daily. New voices, languages and sub-models appear here without anyone editing the site.
About this catalog
Speakshelf is a reference catalog for text to speech voices. Today it carries 4,753 voices from 3 providers in 105 languages, every one with a sample you can play. Voices are grouped the way their providers group them, into model families and engines, so what you hear maps onto what you would deploy.
Speakshelf is independent and not affiliated with Google, Amazon or the Kokoro project. Voice data and audio come from the AI TTS Microservice, a service that unifies Google, Amazon, Azure and other speech providers behind a single endpoint. Samples stream on demand, so listening is free.