Bottom Line Up Front (BLUF): Gemini 3.8 Flash TTS is a NeuralSpace tool that voices text and dialogues: pick the speakers’ voices, accents and style, write the lines and get a finished MP3. Great for podcasts, audiobooks, videos and game scenes.
A dialogue can have several speakers, each with their own voice, accent, style and pace, and the lines are voiced in order. You can also describe the scene, the overall tone and each voice persona, so the result sounds expressive rather than monotone.
30 voices, 8 accents, 6 styles (including whisper and newscaster) and 4 speech paces are available; the temperature slider controls variation. All settings are visible before you start, and the price depends only on the total length of the lines.
The price is shown before you start and is charged exactly as shown. You pay in tokens, with no subscription; if the synthesis fails, the tokens are refunded automatically.
Yes: add as many speakers as you need, give each one a voice and assign the lines between them.
30 voices with 8 accents; for each you can pick a style, pace and voice persona.
The price depends on the total text length and is always shown before you start.