Gemini TTS is an AI voice generator that turns text into expressive speech. Guide delivery and pacing with supported audio tags and style instructions, then preview, generate, and download.
Gemini TTS uses a shared set of preset voices. Choose from the voices shown in AI dubbing.
Generate a voiceover in a language the current mapping includes. The voiceover follows the language of the script. Speech is generated in the language of the script. Generation does not switch the language by itself. To change language, use Translate in the editor, then preview.
Preview the available voices and choose one that fits your script and audience. Voice availability depends on the current integration.
A regional variant is available when it appears in the Gemini voice mapping. The site-wide text-to-speech language list is not the same as this model's coverage.
Other voice models, plus music, sound effects, voice change, and speech to text.
Add supported audio tags and style instructions, then generate a Gemini TTS voiceover for ads, product videos, or narration.