Gemini 2.5 Pro Preview TTS

Neural Network

Beep-boop, writing text for you...
pc1pc2pc3pc4
Main

/

Models

/

Audio AI Models

/

Gemini 2.5 Pro Preview TTS

Specifications

Input
text, images, documents
Output
text, audio
Reasoning effort
low, medium, high
Capabilities
reasoning, function calling
160 $

Prompt cost

(per 1M tokens)

160 $

Answer cost

(per 1M tokens)

0,16 $

Image prompt

(per 1K tokens)

*Prices are shown for API usage via ECO providers.
bothub
BotHub: Try neural networks for freebot

Caps remaining: 0 CAPS
Code example and API for Gemini 2.5 Pro Preview TTSWe offer full access to the OpenAI API through our service. All our endpoints fully comply with OpenAI endpoints and can be used both with plugins and when developing your own software through the SDK.Create API key
import OpenAI from 'openai';
const openai = new OpenAI({
  apiKey: '<your bothub access token>',
  baseURL: 'https://openai.bothub.chat/v1'
});


// Sync - Text generation 

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gemini-2.5-pro-preview-tts',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gemini-2.5-pro-preview-tts',
    stream: true
  });

  for await (const chunk of stream) {
    const part: string | null = chunk.choices[0].delta?.content ?? null;
  }
} 
main();

How it works Gemini 2.5 Pro Preview TTS?

Bothubs gather information...empty

Frequently asked questions about Gemini 2.5 Pro Preview TTS

You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

Gemini 2.5 Pro Preview TTS synthesizes speech: it takes text, as well as images and documents, as input and outputs audio. It is suitable for voiceovers for videos and podcasts, audio versions of articles and instructions, and voice responses in applications. Accessible from Russia without a VPN or foreign card.

Technical track parameters, format, and bitrate are not specified in our data, so we cannot provide exact figures: it is easier to check with a test request. What is known is that the model accepts up to 200,000 context tokens and outputs up to 32,000 tokens in the response, so a long script can be submitted in its entirety.

Yes, reasoning before answering is confirmed for the model. In practice, this helps to understand the structure of a long or ambiguous text before voiceover: where a semantic pause is, which fragment to highlight, how to read an abbreviation or numerical entry. For complex scenarios, this is more important than speed.

Yes, both are supported: the model can call functions and output structured JSON, making it easy to integrate into pipelines and ready-made services. On BotHub, access is via a unified OpenAI-compatible API, so the model can be switched without rewriting the integration.

The model accepts images and documents as input, which is confirmed by our data, so you can give it, for example, a PDF with a script. We have no notes on audio and video input: we do not deny it, but we do not promise it either; check with a test request.

There are no separate measurements for the Russian language in our data, so we will not give estimates: it is more reliable to run your own real text and listen to the result. BotHub itself is Russian-speaking, with interface, support, and payment via Russian cards in rubles, without VPN or a foreign card.

Support ServiceOpen from 10:00 to 18:00 MSK