SpeakshelfGOOGLE CLOUD TEXT TO SPEECH
Every Google voice, on one page.
Play a sample of every voice in the Google Cloud catalog. Filter by model family, language and gender. No account, no setup, just the voices.
10 model families
Google keeps shipping new speech architectures and every generation is still in service. The catalog runs from compact parametric voices to models you can direct with a sentence.
93 languages
Every language has its own page with the full list of voices, so you can link someone straight to one shelf of the catalog.
About this catalog
Google Cloud runs one of the largest text to speech catalogs of any cloud provider. It spans 10 model families, from the WaveNet voices that made neural speech mainstream to Gemini voices that change their delivery when you describe the tone you want. Gemini is really 4 models in one: every Gemini voice can be rendered by any of its sub-models, and each render has its own sample here. Every other voice in the catalog has a sample too.
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.