使用 Gemini API 生成文字轉語音 (TTS)

import FirebaseAILogic

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

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
let config = GenerationConfig(
  responseModalities: [.audio],
  speechConfig: SpeechConfig(voiceName: "Kore", languageCode: "en-US")
)

// Create a `GenerativeModel` instance with a model that supports speech generation.
let model = ai.generativeModel(
  modelName: "gemini-3.1-flash-tts-preview",
  generationConfig: config
)

// Provide a text prompt.
let prompt = "Say cheerfully: Have a wonderful day!"

// Call `generateContent` to generate the speech output based on your text prompt.
let response = try await model.generateContent(prompt)

// Extract the audio data and handle it for downstream use. For example:
for part in response.inlineDataParts {
  let data = part.data          // Raw PCM audio bytes (24kHz, 1 channel, 16-bit)
  let mimeType = part.mimeType  // for example: "audio/pcm"
  print("Received audio data with MIME type: \(mimeType)")

  // To play back raw PCM audio bytes, you'll need to write your own `playRawPcm` function.
  playRawPcm(data: data)
}

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
val config = generationConfig {
    responseModalities = listOf(ResponseModality.AUDIO)
    speechConfig = SpeechConfig(
        voice = Voice("Kore"),
        languageCode = "en-US"
    )
}

// Initialize the Gemini Developer API backend service.
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
    .generativeModel(
        modelName = "gemini-3.1-flash-tts-preview",
        generationConfig = config
    )

// Provide a text prompt.
val prompt = "Say cheerfully: Have a wonderful day!"

// Call `generateContent` to generate the speech output based on your text prompt.
val response = model.generateContent(prompt)

// Extract the audio data and handle it for downstream use. For example:
val part = response.candidates.firstOrNull()?.content?.parts?.firstOrNull()
if (part is InlineDataPart) {
    val pcmData = part.inlineData  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
    val mimeType = part.mimeType   // for example: "audio/pcm"

    // To play back PCM audio data, you'll need to write your own `playAudio` function.
    playAudio(pcmData)
}

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
GenerationConfig config = new GenerationConfig.Builder()
    .setResponseModalities(Collections.singletonList(ResponseModality.AUDIO))
    .setSpeechConfig(new SpeechConfig(new Voice("Kore"), "en-US"))
    .build();

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-3.1-flash-tts-preview", config);

// Use the GenerativeModelFutures Java compatibility layer.
GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide a text prompt.
String prompt = "Say cheerfully: Have a wonderful day!";
Content content = new Content.Builder().addText(prompt).build();
Executor executor = Executors.newSingleThreadExecutor();

// Call `generateContent` to generate the speech output based on your text prompt.
// Extract the audio data and handle it for downstream use.
ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        Part part = result.getCandidates().get(0).getContent().getParts().get(0);
        if (part instanceof InlineDataPart) {
            byte[] pcmData = ((InlineDataPart) part).getInlineData();
            String mimeType = ((InlineDataPart) part).getMimeType();

            // To play back PCM audio data, you'll need to write your own `playAudio` function.
            playAudio(pcmData);
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

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

// TODO(developer): Replace with your app's Firebase configuration
const firebaseConfig = { /* ... */ };
const firebaseApp = initializeApp(firebaseConfig);

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

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
const generationConfig = {
  responseModalities: [ResponseModality.AUDIO],
  speechConfig: {
    voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" } },
    languageCode: "en-US"
  }
};

// Create a `GenerativeModel` instance with a model that supports speech generation.
const model = getGenerativeModel(ai, {
  model: "gemini-3.1-flash-tts-preview",
  generationConfig
});

// Provide a text prompt.
const prompt = "Say cheerfully: Have a wonderful day!";

// Call `generateContent` to generate the speech output based on your text prompt.
const result = await model.generateContent(prompt);
const inlineDataParts = result.response.inlineDataParts();

// Extract the audio data and handle it for downstream use. For example:
if (inlineDataParts?.[0]) {
  const pcmBase64 = inlineDataParts[0].inlineData.data;
  // Decode base64 to ArrayBuffer
  const pcmBuffer = Uint8Array.from(atob(pcmBase64), c => c.charCodeAt(0)).buffer;

  // To play back a PCM buffer, you'll need to write your own `playAudio` function.
  playAudio(pcmBuffer);
}

import 'package:firebase_ai/firebase_ai.dart';

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
final config = GenerationConfig(
  responseModalities: [ResponseModality.audio],
  speechConfig: SpeechConfig(voiceName: 'Kore', languageCode: 'en-US'),
);

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-3.1-flash-tts-preview',
  config: config,
);

// Provide a text prompt.
final prompt = 'Say cheerfully: Have a wonderful day!';

// Call `generateContent` to generate the speech output based on your text prompt.
final response = await model.generateContent([Content.text(prompt)]);

// Extract the audio data and handle it for downstream use. For example:
final part = response.candidates.first.content.parts.first;
if (part is InlineDataPart && part.mimeType.startsWith('audio/')) {
  final Uint8List pcmData = part.bytes;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)

  // To play back PCM audio data, you'll need to write your own `playAudio` function.
  await playAudio(pcmData);
}

using Firebase.AI;

// Set `responseModalities` to include `Audio`.
// Configure a `SpeechConfig` with your chosen voice name and language code.
var config = new GenerationConfig(
  responseModalities: new System.Collections.Generic.List<ResponseModality> { ResponseModality.Audio },
  speechConfig: SpeechConfig.UsePrebuiltVoice("Kore", "en-US")
);

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

// Create a `GenerativeModel` instance with a model that supports speech generation.
var model = ai.GetGenerativeModel(
  modelName: "gemini-3.1-flash-tts-preview",
  generationConfig: config
);

// Provide a text prompt.
var prompt = "Say cheerfully: Have a wonderful day!";

// Call `GenerateContentAsync` to generate the speech output based on your text prompt.
var response = await model.GenerateContentAsync(prompt);

// Extract the audio data and handle it for downstream use. For example:
if (response.Candidates.Count > 0) {
  foreach (var part in response.Candidates[0].Content.Parts) {
    if (part is ModelContent.InlineDataPart inlineData) {
      byte[] pcmData = inlineData.Data;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)

      // To play back PCM audio data, you'll need to write your own `playAudio` function.
      playAudio(pcmData);
    }
  }
}

import FirebaseAILogic

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

// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
let multiSpeechConfig = SpeechConfig(
  multiSpeakerVoiceConfig: MultiSpeakerVoiceConfig(
    speakerVoiceConfigs: [
      SpeakerVoiceConfig(speaker: "Joe", voiceName: "Puck"),
      SpeakerVoiceConfig(speaker: "Jane", voiceName: "Kore")
    ]
  ),
  languageCode: "en-US"
)

// Set `responseModalities` to include `audio`.
let config = GenerationConfig(
  responseModalities: [.audio],
  speechConfig: multiSpeechConfig
)

// Create a `GenerativeModel` instance with a model that supports speech generation.
let model = ai.generativeModel(
  modelName: "gemini-3.1-flash-tts-preview",
  generationConfig: config
)

// Provide a text prompt that includes the names of the speakers.
let prompt = """
Joe: How's it going today Jane?
Jane: Not too bad, how about you?
"""

// Call `generateContent` to generate the speech output based on your text prompt.
let response = try await model.generateContent(prompt)

// Extract the audio data and handle it for downstream use. For example:
for part in response.inlineDataParts {
  let data = part.data          // Raw PCM audio bytes (24kHz, 1 channel, 16-bit)
  let mimeType = part.mimeType  // for example: "audio/pcm"
  print("Received audio data with MIME type: \(mimeType)")

  // To play back raw PCM audio bytes, you'll need to write your own `playRawPcm` function.
  playRawPcm(data: data)
}

// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
val multiSpeechConfig = SpeechConfig(
    multiSpeakerVoiceConfig = MultiSpeakerVoiceConfig(
        speakerVoiceConfigs = listOf(
            SpeakerVoiceConfig(speaker = "Joe", voice = Voice("Puck")),
            SpeakerVoiceConfig(speaker = "Jane", voice = Voice("Kore"))
        )
    ),
    languageCode = "en-US"
)

// Set `responseModalities` to include `AUDIO`.
val config = generationConfig {
    responseModalities = listOf(ResponseModality.AUDIO)
    speechConfig = multiSpeechConfig
}

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
    .generativeModel(
        modelName = "gemini-3.1-flash-tts-preview",
        generationConfig = config
    )

// Provide a text prompt that includes the names of the speakers.
val prompt = """
Joe: How's it going today Jane?
Jane: Not too bad, how about you?
"""

// Call `generateContent` to generate the speech output based on your text prompt.
val response = model.generateContent(prompt)

// Extract the audio data and handle it for downstream use. For example:
val part = response.candidates.firstOrNull()?.content?.parts?.firstOrNull()
if (part is InlineDataPart) {
    val pcmData = part.inlineData  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
    val mimeType = part.mimeType   // for example: "audio/pcm"

    // To play back PCM audio data, you'll need to write your own `playAudio` function.
    playAudio(pcmData)
}

// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
MultiSpeakerVoiceConfig multiSpeakerVoiceConfig = new MultiSpeakerVoiceConfig(
    Arrays.asList(
        new SpeakerVoiceConfig("Joe", new Voice("Puck")),
        new SpeakerVoiceConfig("Jane", new Voice("Kore"))
    )
);

SpeechConfig multiSpeechConfig = new SpeechConfig(multiSpeakerVoiceConfig);

// Set `responseModalities` to include `AUDIO`.
GenerationConfig config = new GenerationConfig.Builder()
    .setResponseModalities(Collections.singletonList(ResponseModality.AUDIO))
    .setSpeechConfig(multiSpeechConfig)
    .build();

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
         .generativeModel("gemini-3.1-flash-tts-preview", config);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide a text prompt that includes the names of the speakers.
String prompt = "Joe: How's it going today Jane?\nJane: Not too bad, how about you?";
Content content = new Content.Builder().addText(prompt).build();
Executor executor = Executors.newSingleThreadExecutor();

// Call `generateContent` to generate the speech output based on your text prompt.
// Extract the audio data and handle it for downstream use.
ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        Part part = result.getCandidates().get(0).getContent().getParts().get(0);
        if (part instanceof InlineDataPart) {
            byte[] pcmData = ((InlineDataPart) part).getInlineData();  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
            String mimeType = ((InlineDataPart) part).getMimeType();   // for example: "audio/pcm"

            // To play back PCM audio data, you'll need to write your own `playAudio` function.
            playAudio(pcmData);
        }
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

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

// TODO(developer): Replace with your app's Firebase configuration
const firebaseConfig = { /* ... */ };
const firebaseApp = initializeApp(firebaseConfig);

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

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
const generationConfig = {
  responseModalities: [ResponseModality.AUDIO],
  speechConfig: {
    multiSpeakerVoiceConfig: {
      speakerVoiceConfigs: [
        { speaker: "Joe", voiceConfig: { prebuiltVoiceConfig: { voiceName: "Puck" } } },
        { speaker: "Jane", voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" } } }
      ]
    },
    languageCode: "en-US"
  }
};

// Create a `GenerativeModel` instance with a model that supports speech generation.
const model = getGenerativeModel(ai, {
  model: "gemini-3.1-flash-tts-preview",
  generationConfig
});

// Provide a text prompt that includes the names of the speakers.
const prompt = `
Joe: How's it going today Jane?
Jane: Not too bad, how about you?
`;

// Call `generateContent` to generate the speech output based on your text prompt.
const result = await model.generateContent(prompt);
const inlineDataParts = result.response.inlineDataParts();

// Extract the audio data and handle it for downstream use. For example:
if (inlineDataParts?.[0]) {
  const pcmBase64 = inlineDataParts[0].inlineData.data;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
  const pcmBuffer = Uint8Array.from(atob(pcmBase64), c => c.charCodeAt(0)).buffer;

  // To play back a PCM buffer, you'll need to write your own `playAudio` function.
  playAudio(pcmBuffer);
}

import 'package:firebase_ai/firebase_ai.dart';

// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
final multiSpeechConfig = SpeechConfig.multiSpeaker(
  multiSpeakerVoiceConfig: MultiSpeakerVoiceConfig(
    speakerVoiceConfigs: [
      SpeakerVoiceConfig(speaker: 'Joe', voiceName: 'Puck'),
      SpeakerVoiceConfig(speaker: 'Jane', voiceName: 'Kore'),
    ],
  ),
  languageCode: 'en-US',
);

// Set `responseModalities` to include `audio`.
final config = GenerationConfig(
  responseModalities: [ResponseModality.audio],
  speechConfig: multiSpeechConfig,
);

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-3.1-flash-tts-preview',
  config: config,
);

// Provide a text prompt that includes the names of the speakers.
final prompt = '''
Joe: How's it going today Jane?
Jane: Not too bad, how about you?
''';

// Call `generateContent` to generate the speech output based on your text prompt.
final response = await model.generateContent([Content.text(prompt)]);

// Extract the audio data and handle it for downstream use. For example:
final part = response.candidates.first.content.parts.first;
if (part is InlineDataPart && part.mimeType.startsWith('audio/')) {
  final Uint8List pcmData = part.bytes;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)

  // To play back PCM audio data, you'll need to write your own `playAudio` function.
  await playAudio(pcmData);
}

using Firebase.AI;

// Configure a `SpeechConfig` for multiple speakers, assigning a voice to each speaker.
var multiSpeakerVoiceConfig = new MultiSpeakerVoiceConfig(
  new System.Collections.Generic.List<SpeakerVoiceConfig> {
    SpeakerVoiceConfig.UsePrebuiltVoice("Joe", "Puck"),
    SpeakerVoiceConfig.UsePrebuiltVoice("Jane", "Kore")
  }
);

var multiSpeechConfig = SpeechConfig.UseMultiSpeakerVoice(multiSpeakerVoiceConfig);

// Set `responseModalities` to include `Audio`.
var config = new GenerationConfig(
  responseModalities: new System.Collections.Generic.List<ResponseModality> { ResponseModality.Audio },
  speechConfig: multiSpeechConfig
);

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

// Create a `GenerativeModel` instance with a model that supports speech generation.
var model = ai.GetGenerativeModel(
  modelName: "gemini-3.1-flash-tts-preview",
  generationConfig: config
);

// Provide a text prompt that includes the names of the speakers.
var prompt = "Joe: How's it going today Jane?\nJane: Not too bad, how about you?";

// Call `GenerateContentAsync` to generate the speech output based on your text prompt.
var response = await model.GenerateContentAsync(prompt);

// Extract the audio data and handle it for downstream use. For example:
if (response.Candidates.Count > 0) {
  foreach (var part in response.Candidates[0].Content.Parts) {
    if (part is ModelContent.InlineDataPart inlineData) {
      byte[] pcmData = inlineData.Data;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)

      // To play back PCM audio data, you'll need to write your own `playAudio` function.
      playAudio(pcmData);
    }
  }
}

import FirebaseAILogic

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

// Set `responseModalities` to include `audio`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
let config = GenerationConfig(
  responseModalities: [.audio],
  speechConfig: SpeechConfig(voiceName: "Kore")
)

// Create a `GenerativeModel` instance with a model that supports speech generation.
let model = ai.generativeModel(
  modelName: "gemini-3.1-flash-tts-preview",
  generationConfig: config
)

// Provide a text prompt.
let prompt = "Tell me a story about a brave knight."

// Call `generateContentStream` to generate the speech output stream based on your text prompt.
let responseStream = try model.generateContentStream(prompt)

// Extract the audio data and handle it for downstream use. For example:
for try await chunk in responseStream {
  for part in chunk.inlineDataParts {
    let data = part.data          // Raw PCM audio bytes (24kHz, 1 channel, 16-bit)
    let mimeType = part.mimeType  // for example: "audio/pcm"

    // Append the audio chunk to your audio queue/buffer for playback.
    appendAudioChunk(data)
  }
}

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
val config = generationConfig {
    responseModalities = listOf(ResponseModality.AUDIO)
    speechConfig = SpeechConfig(voice = Voice("Kore"))
}

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
    .generativeModel(
        modelName = "gemini-3.1-flash-tts-preview",
        generationConfig = config
    )

// Provide a text prompt.
val prompt = "Tell me a story about a brave knight."

// Call `generateContentStream` to generate the speech output stream based on your text prompt.
// Extract the audio data and handle it for downstream use.
model.generateContentStream(prompt).collect { chunk ->
    val part = chunk.candidates.firstOrNull()?.content?.parts?.firstOrNull()
    if (part is InlineDataPart) {
        val pcmChunk = part.inlineData  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
        val mimeType = part.mimeType    // for example: "audio/pcm"

        // Append the audio chunk to your audio queue/buffer for playback.
        appendAudioChunk(pcmChunk)
    }
}

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
GenerationConfig config = new GenerationConfig.Builder()
    .setResponseModalities(Collections.singletonList(ResponseModality.AUDIO))
    .setSpeechConfig(new SpeechConfig(new Voice("Kore")))
    .build();

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-3.1-flash-tts-preview", config);

GenerativeModelFutures model = GenerativeModelFutures.from(ai);

// Provide a text prompt.
String prompt = "Tell me a story about a brave knight.";
Content content = new Content.Builder().addText(prompt).build();

// Call `generateContentStream` to generate the speech output stream based on your text prompt.
Publisher<GenerateContentResponse> streamingResponse =
    model.generateContentStream(content);

// Extract the audio data and handle it for downstream use.
streamingResponse.subscribe(new Subscriber<GenerateContentResponse>() {
  @Override
  public void onSubscribe(Subscription s) {
      s.request(Long.MAX_VALUE);
  }

  @Override
  public void onNext(GenerateContentResponse chunk) {
      Part part = chunk.getCandidates().get(0).getContent().getParts().get(0);
      if (part instanceof InlineDataPart) {
          byte[] pcmChunk = ((InlineDataPart) part).getInlineData();  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
          String mimeType = ((InlineDataPart) part).getMimeType();    // for example: "audio/pcm"

          // Append the audio chunk to your audio queue/buffer for playback.
          appendAudioChunk(pcmChunk);
      }
  }

  @Override
  public void onComplete() {
      // Audio stream complete.
  }

  @Override
  public void onError(Throwable t) {
      t.printStackTrace();
  }
});

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

// TODO(developer): Replace with your app's Firebase configuration
const firebaseConfig = { /* ... */ };
const firebaseApp = initializeApp(firebaseConfig);

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

// Set `responseModalities` to include `AUDIO`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
const generationConfig = {
  responseModalities: [ResponseModality.AUDIO],
  speechConfig: {
    voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" } }
  }
};

// Create a `GenerativeModel` instance with a model that supports speech generation.
const model = getGenerativeModel(ai, {
  model: "gemini-3.1-flash-tts-preview",
  generationConfig
});

// Provide a text prompt.
const prompt = "Tell me a story about a brave knight.";

// Call `generateContentStream` to generate the speech output stream based on your text prompt.
const result = await model.generateContentStream(prompt);

// Extract the audio data and handle it for downstream use. For example:
const playbackQueue = [];
for await (const chunk of result.stream) {
  const inlineDataParts = chunk.inlineDataParts();
  if (inlineDataParts?.[0]) {
    const pcmBase64 = inlineDataParts[0].inlineData.data;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)
    const pcmBuffer = Uint8Array.from(atob(pcmBase64), c => c.charCodeAt(0)).buffer;

    // Append the audio chunk to your audio queue/buffer for playback.
    playbackQueue.push(pcmBuffer);
  }
}

// To play back an array of PCM buffers in sequence, you'll need to write your own `processPlaybackQueue` function.
processPlaybackQueue(playbackQueue);

import 'package:firebase_ai/firebase_ai.dart';

// Set `responseModalities` to include `audio`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
final config = GenerationConfig(
  responseModalities: [ResponseModality.audio],
  speechConfig: SpeechConfig(voiceName: 'Kore'),
);

// Initialize the Gemini Developer API backend service.
// Create a `GenerativeModel` instance with a model that supports speech generation.
final model = FirebaseAI.googleAI().generativeModel(
  model: 'gemini-3.1-flash-tts-preview',
  config: config,
);

// Provide a text prompt.
final prompt = 'Tell me a story about a brave knight.';

// Call `generateContentStream` to generate the speech output stream based on your text prompt.
final responseStream = model.generateContentStream([Content.text(prompt)]);

// Extract the audio data and handle it for downstream use. For example:
await for (final chunk in responseStream) {
  final part = chunk.candidates.first.content.parts.first;
  if (part is InlineDataPart && part.mimeType.startsWith('audio/')) {
    final Uint8List pcmChunk = part.bytes;  // Raw PCM bytes (24kHz, 1 channel, 16-bit)

    // Append the audio chunk to your audio queue/buffer for playback.
    appendAudioChunk(pcmChunk);
  }
}

using System.Collections.Generic;
using System.Linq;
using Firebase.AI;

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

// Set `ResponseModalities` to include `Audio`.
// Configure a `SpeechConfig` with your chosen voice name (and optionally a language code).
var config = new GenerationConfig(
    responseModalities: new List<ResponseModality> { ResponseModality.Audio },
    speechConfig: SpeechConfig.UsePrebuiltVoice("Kore")
);

// Create a `GenerativeModel` instance with a model that supports speech generation.
var model = ai.GetGenerativeModel(
    modelName: "gemini-3.1-flash-tts-preview",
    generationConfig: config
);

// Provide a text prompt.
var prompt = "Tell me a story about a brave knight.";

// Call `GenerateContentStreamAsync` to generate the speech output stream based on your text prompt.
var responseStream = model.GenerateContentStreamAsync(prompt);

// Extract the audio data and handle it for downstream use. For example:
await foreach (var response in responseStream)
{
    var audioParts = response.Candidates.FirstOrDefault().Content.Parts
                            .OfType<ModelContent.InlineDataPart>();

    foreach (var part in audioParts)
    {
        byte[] pcmChunk = part.Data; // Raw PCM bytes (24kHz, 1 channel, 16-bit)

        // Append the audio chunk to your audio queue/buffer for playback.
        appendAudioChunk(pcmChunk);
    }
}