Google Gemini 2.5 Pro Text to Speech uses Google's highest-quality speech model to read your text aloud with clear, natural, expressive delivery. Pick one of 30 prebuilt voices from the dropdown, each with its own character such as bright, firm, warm, or informative, and choose the spoken language from the second dropdown (auto-detect by default; Chinese, English, Japanese, Korean, French, German, Spanish and many more are supported). You can also steer the delivery in plain language, for example by starting with "Say excitedly:" or "Whisper:", and the model adjusts emotion, pace and tone accordingly. Split very long content into parts, as quality may degrade on multi-minute continuous narration. Great for audiobooks, e-learning narration, podcast intros, product explainers and accessibility audio. Text input is limited to 8,192 tokens and the audio is delivered as MP3. Prompt example 1: Say it in a low, mysterious voice: As midnight struck, the candles along the castle hallway went out one by one, leaving only distant footsteps. Prompt example 2: Say excitedly: Welcome back to Curiosity Lab! Today we're building an erupting mini volcano. Got your baking soda and vinegar ready? Prompt example 3: Say it in a warm, steady voice: Welcome to Gallery Two. This Qing dynasty blue-and-white vase is painted with lotus scrolls for endless blessings. Prompt example 4: Whisper: Shh, don't make a sound. Just a little longer, and the fireflies will start glowing one by one in the grass. Prompt example 5: Say it like a mellow late-night radio host: It's midnight. If you're still awake, maybe you're missing someone too. This next song is for you. Prompt example 6: (Spoken language: French) Bonjour, je voudrais un croissant et un café au lait, s'il vous plaît. Merci beaucoup ! Prompt example 7: Say it clearly with crisp articulation: She sells seashells by the seashore, and the shells she sells are seashells, I'm sure. Prompt example 8: Say it in a deep, powerful movie-trailer voice: In a world that has lost its light, only one person dares to light the final lamp. Prompt example 9: Say it like a bold traditional storyteller: That night, as snow filled the sky, the greatest swordsman alive climbed the mountain alone, his blade colder than the snow. Prompt example 10: Say it tenderly: My dear, the osmanthus in our yard is blooming again and the house smells sweet. I often think of our evening walks together. Maximum context window (input and output combined): about 24,576 tokens. Maximum total input per request (including history): 8,192 tokens. Maximum output per reply: about 16,384 tokens (model reasoning, if any, counts toward this limit). Output content formats: Audio Pricing: Medium-high Audio output format: MP3. Continuous conversation: Not supported AI can make mistakes. Please verify important information.