Cómo analizar archivos de audio con la API de Gemini

Organiza tus páginas con colecciones Guarda y categoriza el contenido según tus preferencias.

import FirebaseAI

// Initialize the Gemini Developer API backend service
let ai = FirebaseAI.firebaseAI(backend: .googleAI())

// Create a `GenerativeModel` instance with a model that supports your use case
let model = ai.generativeModel(modelName: "gemini-2.0-flash")


// Provide the audio as `Data`
guard let audioData = try? Data(contentsOf: audioURL) else {
    print("Error loading audio data.")
    return // Or handle the error appropriately
}

// Specify the appropriate audio MIME type
let audio = InlineDataPart(data: audioData, mimeType: "audio/mpeg")


// Provide a text prompt to include with the audio
let prompt = "Transcribe what's said in this audio recording."

// To stream generated text output, call `generateContentStream` with the audio and text prompt
let contentStream = try model.generateContentStream(audio, prompt)

// Print the generated text, handling the case where it might be nil
for try await chunk in contentStream {
    if let text = chunk.text {
        print(text)
    }
}

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
                        .generativeModel("gemini-2.0-flash")


val contentResolver = applicationContext.contentResolver

val inputStream = contentResolver.openInputStream(audioUri)

if (inputStream != null) {  // Check if the audio loaded successfully
    inputStream.use { stream ->
        val bytes = stream.readBytes()

        // Provide a prompt that includes the audio specified above and text
        val prompt = content {
            inlineData(bytes, "audio/mpeg")  // Specify the appropriate audio MIME type
            text("Transcribe what's said in this audio recording.")
        }

        // To stream generated text output, call `generateContentStream` with the prompt
        var fullResponse = ""
        generativeModel.generateContentStream(prompt).collect { chunk ->
            // Log the generated text, handling the case where it might be null
            Log.d(TAG, chunk.text?: "")
            fullResponse += chunk.text?: ""
        }
    }
} else {
    Log.e(TAG, "Error getting input stream for audio.")
    // Handle the error appropriately
}

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-2.0-flash");

// Use the GenerativeModelFutures Java compatibility layer which offers
// support for ListenableFuture and Publisher APIs
GenerativeModelFutures model = GenerativeModelFutures.from(ai);


ContentResolver resolver = getApplicationContext().getContentResolver();

try (InputStream stream = resolver.openInputStream(audioUri)) {
    File audioFile = new File(new URI(audioUri.toString()));
    int audioSize = (int) audioFile.length();
    byte audioBytes = new byte[audioSize];
    if (stream != null) {
        stream.read(audioBytes, 0, audioBytes.length);
        stream.close();

        // Provide a prompt that includes the audio specified above and text
        Content prompt = new Content.Builder()
              .addInlineData(audioBytes, "audio/mpeg")  // Specify the appropriate audio MIME type
              .addText("Transcribe what's said in this audio recording.")
              .build();

        // To stream generated text output, call `generateContentStream` with the prompt
        Publisher<GenerateContentResponse> streamingResponse =
                model.generateContentStream(prompt);

        StringBuilder fullResponse = new StringBuilder();
        streamingResponse.subscribe(new Subscriber<GenerateContentResponse>() {
            @Override
            public void onNext(GenerateContentResponse generateContentResponse) {
                String chunk = generateContentResponse.getText();
                String text = (chunk == null) ? "" : chunk;
                Log.d(TAG, text);
                fullResponse.append(text);
            }
            @Override
            public void onComplete() {
                Log.d(TAG, fullResponse.toString());
            }
            @Override
            public void onError(Throwable t) {
                Log.e(TAG, "Failed to generate a response", t);
            }
            @Override
            public void onSubscribe(Subscription s) {
            }
         });
    } else {
        Log.e(TAG, "Error getting input stream for file.");
        // Handle the error appropriately
    }
} catch (IOException e) {
    Log.e(TAG, "Failed to read the audio file", e);
} catch (URISyntaxException e) {
    Log.e(TAG, "Invalid audio file", e);
}

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, { model: "gemini-2.0-flash" });


// Converts a File object to a Part object.
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(','));
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

async function run() {
  // Provide a text prompt to include with the audio
  const prompt = "Transcribe what's said in this audio recording.";

  // Prepare audio for input
  const fileInputEl = document.querySelector("input[type=file]");
  const audioPart = await fileToGenerativePart(fileInputEl.files);

  // To stream generated text output, call `generateContentStream` with the text and audio
  const result = await model.generateContentStream([prompt, audioPart]);

  // Log the generated text
  for await (const chunk of result.stream) {
    const chunkText = chunk.text();
    console.log(chunkText);
  }
}

run();

import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

// Initialize FirebaseApp
await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
final model =
      FirebaseAI.googleAI().generativeModel(model: 'gemini-2.0-flash');


// Provide a text prompt to include with the audio
final prompt = TextPart("Transcribe what's said in this audio recording.");

// Prepare audio for input
final audio = await File('audio0.mp3').readAsBytes();

// Provide the audio as `Data` with the appropriate audio MIME type
final audioPart = InlineDataPart('audio/mpeg', audio);

// To stream generated text output, call `generateContentStream` with the text and audio
final response = await model.generateContentStream([
  Content.multi([prompt, audioPart])
]);

// Print the generated text
await for (final chunk in response) {
  print(chunk.text);
}

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());

// Create a `GenerativeModel` instance with a model that supports your use case
var model = ai.GetGenerativeModel(modelName: "gemini-2.0-flash");


// Provide a text prompt to include with the audio
var prompt = ModelContent.Text("Transcribe what's said in this audio recording.");

// Provide the audio as `data` with the appropriate audio MIME type
var audio = ModelContent.InlineData("audio/mpeg",
      System.IO.File.ReadAllBytes(System.IO.Path.Combine(
        UnityEngine.Application.streamingAssetsPath, "audio0.mp3")));

// To stream generated text output, call `GenerateContentStreamAsync` with the text and audio
var responseStream = model.GenerateContentStreamAsync(new [] { prompt, audio });

// Print the generated text
await foreach (var response in responseStream) {
  if (!string.IsNullOrWhiteSpace(response.Text)) {
    UnityEngine.Debug.Log(response.Text);
  }
}