UniRouteUniRoute

google / gemini-2-5-pro-tts

Commercial use

Gemini 2.5 Pro Preview TTS is Google’s premium text-to-speech model designed for studio-quality, high-fidelity audio generation. It enables developers to create realistic AI voices with natural language instructions, expressive speech, and long-form audio capabilities.

Pricing: $1.00 in · $20.00 out
View all pricing

google/gemini-2-5-pro-tts USD / 1M tokens

Option / channelInputOutput
Official$1$20

Input

2 / 2
Item 1

Must match dialogue turns

Character persona for this voice

Item 2

Must match dialogue turns

Character persona for this voice

4
Item 1

Must exist in Speakers

Supports audio tags such as [shouting] / [whispers] / [urgency]

Item 2

Must exist in Speakers

Supports audio tags such as [shouting] / [whispers] / [urgency]

Item 3

Must exist in Speakers

Supports audio tags such as [shouting] / [whispers] / [urgency]

Item 4

Must exist in Speakers

Supports audio tags such as [shouting] / [whispers] / [urgency]

Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused. Default value: 1
scene description155/1000
Example Context / Overall Tone165/1000

Output

output typeaudioExample output

README

Complete guide to using google/gemini-2-5-pro-tts