Learn languages naturally with fresh, real content!

Popular Topics
Explore By Region
Google launches new text-to-speech model with 70+ languages and audio tags.
Google has launched the Gemini 3.1 Flash TTS, a new text-to-speech model offering improved expressiveness and developer control.
The system supports over 70 languages, features audio tags for vocal style adjustments, and includes SynthID watermarks to detect AI-generated content.
It is available via the Gemini API and Google AI Studio.
3 Articles
Google lanza un nuevo modelo de texto-a-voz con más de 70 idiomas y etiquetas de audio.