Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window.

Polyglot voices

Overview

Polyglot voices can speak multiple languages.

Each polyglot voice has a language and a speaker number. For example, "fr-FR-Polyglot-1" is speaker 1 in French, "en-US-Polyglot-1" is speaker 1 in American English, and "en-AU-Polyglot-2" is speaker 2 in Australian English.

Example 1. en-US-Polyglot-1 voice

Example 2. en-AU-Polyglot-1 voice

Example 3. es-US-Polyglot-1 voice

Example 4. fr-FR-Polyglot-1 voice

Upon request, polyglot capabilities are also available for a custom voice.

See the Supported Voices page for a complete list of voices available in your language. Text-to-Speech uses a specific voice from this list by setting the VoiceSelectionParams fields when you send a request to the API. See the Text-to-Speech Quickstarts for details on how to send a synthesize request.

Try it for yourself

If you're new to Google Cloud, create an account to evaluate how Text-to-Speech performs in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Try Text-to-Speech free