Gemini TTSNewAudioGoogle Gemini text-to-speech online: 30 natural voices, style and pace control, two-voice dialogues. From 0.5 tokens.
Gemini TTS is Google's speech model (Gemini 3.1 Flash TTS). It voices text with natural voices and intonation and handles Russian well.
Pick one of 30 voices, set a style (e.g. "smiling" or "newscaster") and pace. Dialogue mode splits text into lines for two voices — a ready podcast or scene.
Up to 1,000 characters costs 0.5 tokens, then 1 token per started 1,000 characters.
Yes. In Dialogue mode add lines and pick voices — up to two different voices at once.
Yes, the model detects the language and voices Russian well.
Start generating with Gemini TTS for free. Free tokens on signup.
