Gemini 2.5 Flash Native Audio Latest

Neural Network

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

/

Models

/

Audio AI Models

/

Gemini 2.5 Flash Native Audio Latest

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 Flash Native Audio LatestWe 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-flash-native-audio-latest',
  });
} 

// 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-flash-native-audio-latest',
    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 Flash Native Audio Latest?

Bothubs gather information...empty

Frequently asked questions about Gemini 2.5 Flash Native Audio Latest

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.

This is a Google model with native audio generation: it accepts text, documents, and images, responds with text, and voices the response. It is suitable for voice assistants and conversational scenarios, voicing materials, and working with documents and images when a response is needed in both speech and text.

The model synthesizes speech natively, within the same response, rather than using a separate third-party engine, so the intonation relies on the meaning of the utterance. The context is 200,000 tokens, and the output limit is 32,000 tokens. Specific codecs and bitrates are not specified in our data, so please refer to the API response.

Yes, the model has a declared reasoning mode: before answering, it can break down the task step-by-step. This is noticeable in logic, analysis of long documents, and multi-turn dialogues where it is important to maintain the train of thought. For short utterances, reasoning has almost no effect on speed.

Yes, both function calling and structured JSON output are supported. The model can request the necessary tool itself and return data according to a specified schema, making it convenient to integrate into voice bots, pipelines, and services that require a predictable machine-readable response.

According to our data, in addition to text, images and documents are accepted as input: you can send a screenshot, diagram, photograph, or file and get an analysis. Audio and video input is not noted in the data, so for such scenarios, check the model's response or choose a specialized model from the catalog.

Gemini series models traditionally work with Russian confidently, and this version is designed for multilingual dialogues. There are no formal language evaluations in our data, so please test it in your scenario: in BotHub, this is available without a VPN or foreign card, with payment in rubles.

Support ServiceOpen from 10:00 to 18:00 MSK