Google Gemini 2.5 Flash Text to Speech is Google's low-latency, cost-effective speech model that quickly turns your text into natural, fluent spoken audio, well suited to high-volume or near-real-time voice-over needs. 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 calmly:" or "Say cheerfully:", and the model adjusts emotion, pace and tone accordingly. When you need the highest fidelity and the most refined prosody, switch to Gemini 2.5 Pro Text to Speech. Great for short-video narration, customer-service prompts, course reading, announcements and accessibility audio. Text input is limited to 8,192 tokens and the audio is delivered as MP3. Prompt example 1: Say cheerfully: Congratulations on finishing all of this week's challenges! Your badge is now in your account, so keep it up next week! Prompt example 2: Say calmly: Breathe in slowly and count to four, hold for two seconds, then breathe out and let your shoulders and back fully relax. Prompt example 3: Photosynthesis is how plants use sunlight, water and carbon dioxide to make food while releasing oxygen, a foundation for much of life on Earth. Prompt example 4: Say it clearly and professionally: Our system will be down for maintenance this Saturday from 1 to 3 a.m. We apologize for any inconvenience. Prompt example 5: (Spoken language: Korean) 안녕하세요, 서울 시티투어 버스에 오신 것을 환영합니다. 다음 정류장은 경복궁입니다. Prompt example 6: Say warmly: Welcome to Starlight Cafe! Today's special is the osmanthus oolong latte. Please order at the counter on your left. Prompt example 7: Say it with excitement: It's time for the grand prize draw at our year-end party! And the winner is Alex Chen from Sales. Congratulations! Prompt example 8: Say playfully: Hey kids, there are five birds in a tree. Two fly away. How many birds are left now? Prompt example 9: Say it brightly: Tap the backpack icon at the bottom right to see the treasures you've collected. Try it now! Prompt example 10: Say sincerely and apologetically: We're very sorry. Your item is out of stock and will ship three days late. We'll prioritize your delivery. 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 Audio output format: MP3. Continuous conversation: Not supported AI can make mistakes. Please verify important information.