Phân tích tệp âm thanh bằng API Gemini

import FirebaseAILogic

// 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-3.7-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 generate text output, call `generateContent` with the audio and text prompt
let response = try await model.generateContent(audio, prompt)

// Print the generated text, handling the case where it might be nil
print(response.text ?? "No text in response.")

// 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-3.7-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 generate text output, call `generateContent` with the prompt
        val response = model.generateContent(prompt)

        // Log the generated text, handling the case where it might be null
        Log.d(TAG, response.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-3.7-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 generate text output, call `generateContent` with the prompt
        ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
        Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
            @Override
            public void onSuccess(GenerateContentResponse result) {
                String text = result.getText();
                Log.d(TAG, (text == null) ? "" : text);
            }
            @Override
            public void onFailure(Throwable t) {
                Log.e(TAG, "Failed to generate a response", t);
            }
        }, executor);
    } 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-3.7-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 generate text output, call `generateContent` with the text and audio
  const result = await model.generateContent([prompt, audioPart]);

  // Log the generated text, handling the case where it might be undefined
  console.log(result.response.text() ?? "No text in response.");
}

run();