Interactions API 現已正式發布。建議使用這個 API，存取所有最新功能和模型。

Google 會運用 AI 技術將內容翻譯成你偏好的語言，但可能會出錯。

使用 Lyria 3.5 生成音樂

Lyria 3.5 是 Google 的音樂生成模型系列，可透過 Gemini API 使用。使用 Lyria 3.5，你可以根據文字提示或圖片生成高品質的 44.1 kHz 立體聲音訊。這些模型可提供結構一致的音樂，包括人聲、歌詞時間碼和完整樂器編曲。

Lyria 系列包含以下模型：

模型	模型 ID	適用情境	時間長度	輸出內容
Lyria 3 Clip	`lyria-3-clip-preview`	短片、循環播放、預覽	30 秒	MP3
Lyria 3.5	`lyria-3.5`	包含主歌、副歌和橋段的完整歌曲	幾分鐘 (可使用提示詞控制)	MP3

這兩款模型都可透過新的 Interactions API 使用，支援多模態輸入 (文字和圖片)，並生成 44.1 kHz 高精準度立體聲音訊。

生成音樂短片

Lyria 3 Clip 模型一律會生成 30 秒片段。如要生成短片，請使用文字提示詞呼叫 interactions.create 方法。回覆一律會包含生成的歌詞和歌曲結構，以及 steps 結構定義中的音訊。

Python

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="lyria-3-clip-preview",
    input="A short instrumental acoustic guitar piece.",
)

generated_audio = interaction.output_audio
if generated_audio:
    with open("music.mp3", "wb") as f:
        f.write(base64.b64decode(generated_audio.data))

lyrics = interaction.output_text
if lyrics:
    print(f"Lyrics:\n{lyrics}")

JavaScript

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: 'lyria-3-clip-preview',
    input: 'A short instrumental acoustic guitar piece.',
});

const generatedAudio = interaction.output_audio;
if (generatedAudio) {
  fs.writeFileSync('music.mp3', Buffer.from(generatedAudio.data, 'base64'));
}

const lyrics = interaction.output_text;
if (lyrics) {
  console.log(`Lyrics:\n${lyrics}`);
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Base64;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3-clip-preview"))
        .input(InteractionsInput.of("A short instrumental acoustic guitar piece."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.outputAudio().isPresent() && interaction.outputAudio().get().data().isPresent()) {
  byte[] audioBytes = Base64.getDecoder().decode(interaction.outputAudio().get().data().get());
  Files.write(Paths.get("music.mp3"), audioBytes);
}

interaction.outputText().ifPresent(lyrics -> System.out.println("Lyrics:\n" + lyrics));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "lyria-3-clip-preview",
    "input": "A short instrumental acoustic guitar piece."
}'

您可以使用 interaction.output_audio 屬性擷取生成的音樂資料，該屬性會傳回最後生成的音訊區塊。您也可以使用 interaction.output_text 屬性擷取歌曲的歌詞和結構。如要進一步瞭解便利性屬性，請參閱「互動總覽」。

生成完整歌曲

使用 lyria-3.5 模型生成幾分鐘的完整歌曲。Pro 版模型可理解音樂結構，並創作具有不同主歌、副歌和橋段的樂曲。如要影響時長，可以在提示中指定 (例如「創作 2 分鐘的歌曲」)，或使用時間戳記定義結構。

Python

interaction = client.interactions.create(
    model="lyria-3.5",
    input="An epic cinematic orchestral piece about a journey home. Starts with a solo piano intro, builds through sweeping strings, and climaxes with a massive wall of sound.",
)

JavaScript

const interaction = await client.interactions.create({
    model: 'lyria-3.5',
    input: 'A beautiful piano melody.',
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(
            InteractionsInput.of(
                "An epic cinematic orchestral piece about a journey home. Starts with a solo piano intro, builds through sweeping strings, and climaxes with a massive wall of sound."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "lyria-3.5",
    "input": "A beautiful piano melody."
}'

選取輸出格式

根據預設，Lyria 3.5 模型會以 MP3 格式生成音訊。對於 Lyria 3.5，您也可以設定 response_format，要求以 WAV 格式輸出。

Python

interaction = client.interactions.create(
    model="lyria-3.5",
    input="A beautiful piano melody.",
    response_format={"type": "audio"},
)

JavaScript

const interaction = await client.interactions.create({
    model: 'lyria-3.5',
    input: 'A beautiful piano melody.',
    response_format: {
        type: 'audio',
    },
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AudioResponseFormat;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.CreateModelInteractionResponseFormat;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ResponseFormat;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.of("A beautiful piano melody."))
        .responseFormat(
            CreateModelInteractionResponseFormat.of(
                ResponseFormat.of(AudioResponseFormat.builder().build())))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3.5",
    "input": "A beautiful piano melody.",
    "response_format": {
        "type": "audio"
    }
  }'

剖析回應

Lyria 3.5 的回覆會在 steps 架構中包含多個內容區塊。互動會傳回一系列步驟，其中 model_output 步驟包含生成的內容。文字內容區塊包含生成的歌詞，或是歌曲結構的 JSON 說明。audio 類型的內容區塊包含 Base64 編碼的音訊資料。

Python

lyrics = []
audio_data = None

generated_audio = interaction.output_audio
if generated_audio:
    with open("output.mp3", "wb") as f:
        f.write(base64.b64decode(generated_audio.data))

lyrics = interaction.output_text
if lyrics:
    print(f"Lyrics:\n{lyrics}")

JavaScript

const lyrics = [];
let audioData = null;

const generatedAudio = interaction.output_audio;
if (generatedAudio) {
    fs.writeFileSync("output.mp3", Buffer.from(generatedAudio.data, 'base64'));
}

const lyrics = interaction.output_text;
if (lyrics) {
    console.log("Lyrics:\n" + lyrics);
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Base64;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.of("A song about a starry night."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.outputAudio().isPresent() && interaction.outputAudio().get().data().isPresent()) {
  byte[] audioBytes = Base64.getDecoder().decode(interaction.outputAudio().get().data().get());
  Files.write(Paths.get("output.mp3"), audioBytes);
}

if (interaction.outputText().isPresent()) {
  System.out.println("Lyrics:\n" + interaction.outputText().get());
}

REST

# The output from the REST API is a JSON object containing base64 encoded data.
# You can extract the text or the audio data using a tool like jq.
# To extract the audio and save it to a file:
curl ... | jq -r '.steps[] | select(.type=="model_output") | .content[] | select(.type=="audio") | .data' | base64 -d > output.mp3

交錯顯示歌詞和音樂

Lyria 3.5 的輸出內容相當複雜，包含生成歌詞 (文字) 和歌曲本身 (音訊) 的個別步驟和區塊，因此便利性屬性提供快速且建議的捷徑。

不過，如果您想以程式輔助方式，全面控管伺服器傳回的原始步驟時間軸 (例如記錄收到的個別內容區塊)，可以手動疊代 steps：

Python

lyrics = []
audio_data = None

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "audio":
                audio_data = base64.b64decode(content_block.data)
            elif content_block.type == "text":
                lyrics.append(content_block.text)

if lyrics:
    print("Lyrics:\n" + "\n".join(lyrics))

if audio_data:
    with open("output.mp3", "wb") as f:
        f.write(audio_data)

JavaScript

const lyrics = [];
let audioData = null;

for (const step of interaction.steps) {
    if (step.type === 'model_output') {
        for (const contentBlock of step.content) {
            if (contentBlock.type === 'audio') {
                audioData = Buffer.from(contentBlock.data, 'base64');
            } else if (contentBlock.type === 'text') {
                lyrics.push(contentBlock.text);
            }
        }
    }
}

if (lyrics.length) {
    console.log("Lyrics:\n" + lyrics.join("\n"));
}

if (audioData) {
    fs.writeFileSync("output.mp3", audioData);
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AudioContent;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Base64;
import java.util.List;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.of("A song about a starry night."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

List<String> lyrics = new ArrayList<>();
byte[] audioData = null;

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content contentBlock : outputStep.content().get()) {
          if (contentBlock instanceof AudioContent) {
            AudioContent audioBlock = (AudioContent) contentBlock;
            if (audioBlock.data().isPresent()) {
              audioData = Base64.getDecoder().decode(audioBlock.data().get());
            }
          } else if (contentBlock instanceof TextContent) {
            TextContent textBlock = (TextContent) contentBlock;
            textBlock.text().ifPresent(lyrics::add);
          }
        }
      }
    }
  }
}

if (!lyrics.isEmpty()) {
  System.out.println("Lyrics:\n" + String.join("\n", lyrics));
}

if (audioData != null) {
  Files.write(Paths.get("output.mp3"), audioData);
}

根據圖片生成音樂

Lyria 3.5 支援多模態輸入內容，您可以在 input 清單中提供最多 10 張圖片和文字提示詞，模型就會根據視覺內容創作音樂。

Python

import base64

with open("desert_sunset.jpg", "rb") as f:
    image_bytes = f.read()
    image_b64 = base64.b64encode(image_bytes).decode("utf-8")

response = client.interactions.create(
    model="lyria-3.5",
    input=[
        {
            "type": "text",
            "text": "An atmospheric ambient track inspired by the mood and colors in this image.",
        },
        {
            "type": "image",
            "mime_type": "image/jpeg",
            "data": image_b64,
        },
    ],
)

JavaScript

import * as fs from "fs";

const imageBytes = fs.readFileSync("desert_sunset.jpg").toString("base64");

const interaction = await client.interactions.create({
    model: "lyria-3.5",
    input: [
        {
            type: "text",
            text: "An atmospheric ambient track inspired by the mood and colors in this image.",
        },
        {
            type: "image",
            mime_type: "image/jpeg",
            data: imageBytes,
        },
    ],
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.Base64;
import java.util.List;

Client client = new Client();

byte[] imageBytes = Files.readAllBytes(Paths.get("desert_sunset.jpg"));
String imageB64 = Base64.getEncoder().encodeToString(imageBytes);

Content textContent =
    TextContent.builder()
        .text("An atmospheric ambient track inspired by the mood and colors in this image.")
        .build();
Content imageContent =
    ImageContent.builder()
        .mimeType(ImageContentMimeType.IMAGE_JPEG)
        .data(imageB64)
        .build();

List<Content> contents = Arrays.asList(textContent, imageContent);

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.ofContent(contents))
        .build();

Interaction response =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

# Pass base64 encoded image data directly:
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "lyria-3.5",
    "input": [
      {"type": "text", "text": "An atmospheric ambient track inspired by the mood and colors in this image."},
      {"type": "image", "mime_type": "image/jpeg", "data": "/9j/4AAQSkZJRgABAQEASABIAAD/2wBDAP//////////////////////////////////////////////////////////////////////////////////////wgALCAABAAEBAREA/8QAFBABAAAAAAAAAAAAAAAAAAAAAP/aAAgBAQABPxA="}
    ]
  }'

提供自訂歌詞

你可以自行撰寫歌詞，並加入提示。使用 [Verse]、[Chorus] 和 [Bridge] 等區段標記，協助模型瞭解歌曲結構：

Python

prompt = """
Create a dreamy indie pop song with the following lyrics:

[Verse 1]
Walking through the neon glow,
city lights reflect below,
every shadow tells a story,
every corner, fading glory.

[Chorus]
We are the echoes in the night,
burning brighter than the light,
hold on tight, don't let me go,
we are the echoes down below.

[Verse 2]
Footsteps lost on empty streets,
rhythms sync to heartbeats,
whispers carried by the breeze,
dancing through the autumn leaves.
"""

interaction = client.interactions.create(
    model="lyria-3.5",
    input=prompt,
)

JavaScript

const prompt = `
Create a dreamy indie pop song with the following lyrics:

[Verse 1]
Walking through the neon glow,
city lights reflect below,
every shadow tells a story,
every corner, fading glory.

[Chorus]
We are the echoes in the night,
burning brighter than the light,
hold on tight, don't let me go,
we are the echoes down below.

[Verse 2]
Footsteps lost on empty streets,
rhythms sync to heartbeats,
whispers carried by the breeze,
dancing through the autumn leaves.
`;

const interaction = await client.interactions.create({
    model: 'lyria-3.5',
    input: prompt,
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

String prompt =
    "Create a dreamy indie pop song with the following lyrics:\n\n"
        + "[Verse 1]\n"
        + "Walking through the neon glow,\n"
        + "city lights reflect below,\n"
        + "every shadow tells a story,\n"
        + "every corner, fading glory.\n\n"
        + "[Chorus]\n"
        + "We are the echoes in the night,\n"
        + "burning brighter than the light,\n"
        + "hold on tight, don't let me go,\n"
        + "we are the echoes down below.\n\n"
        + "[Verse 2]\n"
        + "Footsteps lost on empty streets,\n"
        + "rhythms sync to heartbeats,\n"
        + "whispers carried by the breeze,\n"
        + "dancing through the autumn leaves.";

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.of(prompt))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3.5",
    "input": "Create a dreamy indie pop song with the following lyrics: ..."
  }'

控制時間和結構

你可以使用時間戳記，指定歌曲在特定時間點發生的事件。這項功能有助於控制樂器進入的時間、歌詞的傳送時間，以及歌曲的進展方式：

Python

prompt = """
[0:00 - 0:10] Intro: Begin with a soft lo-fi beat and muffled
              vinyl crackle.
[0:10 - 0:30] Verse 1: Add a warm Fender Rhodes piano melody
              and gentle vocals singing about a rainy morning.
[0:30 - 0:50] Chorus: Full band with upbeat drums and soaring
              synth leads. The lyrics are hopeful and uplifting.
[0:50 - 1:00] Outro: Fade out with the piano melody alone.
"""

interaction = client.interactions.create(
    model="lyria-3.5",
    input=prompt,
)

JavaScript

const prompt = `
[0:00 - 0:10] Intro: Begin with a soft lo-fi beat and muffled
              vinyl crackle.
[0:10 - 0:30] Verse 1: Add a warm Fender Rhodes piano melody
              and gentle vocals singing about a rainy morning.
[0:30 - 0:50] Chorus: Full band with upbeat drums and soaring
              synth leads. The lyrics are hopeful and uplifting.
[0:50 - 1:00] Outro: Fade out with the piano melody alone.
`;

const interaction = await client.interactions.create({
    model: 'lyria-3.5',
    input: prompt,
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

String prompt =
    "[0:00 - 0:10] Intro: Begin with a soft lo-fi beat and muffled vinyl crackle.\n"
        + "[0:10 - 0:30] Verse 1: Add a warm Fender Rhodes piano melody and gentle vocals singing about a rainy morning.\n"
        + "[0:30 - 0:50] Chorus: Full band with upbeat drums and soaring synth leads. The lyrics are hopeful and uplifting.\n"
        + "[0:50 - 1:00] Outro: Fade out with the piano melody alone.";

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(InteractionsInput.of(prompt))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3.5",
    "input": "[0:00 - 0:10] Intro: ..."
  }'

生成配樂

如要製作背景音樂、遊戲配樂或任何不需要人聲的音樂，可以提示模型製作純樂器演奏的曲目：

Python

interaction = client.interactions.create(
    model="lyria-3-clip-preview",
    input="A bright chiptune melody in C Major, retro 8-bit video game style. Instrumental only, no vocals.",
)

JavaScript

const interaction = await client.interactions.create({
    model: 'lyria-3-clip-preview',
    input: 'A bright chiptune melody in C Major, retro 8-bit video game style. Instrumental only, no vocals.',
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3-clip-preview"))
        .input(
            InteractionsInput.of(
                "A bright chiptune melody in C Major, retro 8-bit video game style. Instrumental only, no vocals."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3-clip-preview",
    "input": "A bright chiptune melody in C Major, retro 8-bit video game style. Instrumental only, no vocals."
  }'

生成不同語言的音樂

Lyria 3.5 會以提示詞的語言生成歌詞。如要生成法文歌詞的歌曲，請用法文撰寫提示。模型會根據語言調整語音風格和發音。

Python

interaction = client.interactions.create(
    model="lyria-3.5",
    input="Crée une chanson pop romantique en français sur un coucher de soleil à Paris. Utilise du piano et de la guitare acoustique.",
)

JavaScript

const interaction = await client.interactions.create({
    model: 'lyria-3.5',
    input: 'Crée une chanson pop romantique en français sur un coucher de soleil à Paris. Utilise du piano et de la guitare acoustique.',
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("lyria-3.5"))
        .input(
            InteractionsInput.of(
                "Crée une chanson pop romantique en français sur un coucher de soleil à Paris. Utilise du piano et de la guitare acoustique."))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lyria-3.5",
    "input": "Crée une chanson pop romantique en français sur un coucher de soleil à Paris. Utilise du piano et de la guitare acoustique."
  }'

模型智慧

Lyria 3.5 會分析提示程序，模型會根據提示推斷音樂結構 (前奏、主歌、副歌、橋段等)。這項程序會在生成音訊前執行，確保結構一致性和音樂性。

提示指南

如要瞭解如何撰寫有效的提示詞，指定音樂類型、樂器、歌曲結構、自訂歌詞和演唱風格，請參閱 Lyria 提示詞指南。

最佳做法

先使用 Clip 進行疊代。使用速度較快的 lyria-3-clip-preview 模型測試提示，再使用 lyria-3.5 生成完整長度的內容。
提供清楚明確的說明，籠統的提示詞只會產出一般結果。提及樂器、BPM、調性、情境和結構，以獲得最佳輸出內容。
語言相符。以所需語言輸入提示。
使用章節標記。[Verse]、[Chorus]、[Bridge] 標記可為模型提供清楚的結構。
歌詞和指示分開。提供自訂歌詞時，請清楚區分歌詞和音樂方向指示。

限制

安全性：所有提示都會經過安全篩選器檢查。系統會封鎖觸發篩選器的提示。包括要求特定藝人聲音的提示，或是生成受著作權保護的歌詞。
浮水印：所有生成的音訊都會加上 SynthID 音訊浮水印，以利識別。這種浮水印人耳無法辨識，也不會影響聆聽體驗。
多輪遞進編輯：音樂生成是單輪程序。目前版本的 Lyria 3.5 不支援透過多個提示，反覆編輯或修正生成的片段。
長度：片段模型一律會生成 30 秒的片段。Pro 模型會生成幾分鐘的歌曲，確切時長取決於提示。
決定性：即使使用相同提示，每次通話的結果也可能不同。

後續步驟

查看 Lyria 3.5 模型的價格。
試試 Lyria RealTime，即時串流音樂生成。
使用 TTS 模型生成多人對話。
瞭解如何生成圖片或影片。
瞭解 Gemini 如何解讀音訊檔案。
使用 Live API 與 Gemini 即時對話。