使用 Lyria 3 生成音樂

Lyria 3 是 Google 的音樂生成模型系列，可透過 Gemini API 使用。使用 Lyria 3，你可以根據文字提示詞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內容，包括人聲、歌詞時間碼和完整樂器編曲。

Lyria 3 系列包含兩種模型：

型號 模型 ID 適用情境 時間長度 輸出
Lyria 3 Clip lyria-3-clip-preview 短片、循環播放、預覽 30 秒 MP3
Lyria 3 Pro lyria-3-pro-preview 包含主歌、副歌和橋段的完整歌曲 幾分鐘 (可使用提示控制) 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)，並產生 44.1 kHz 高保真立體聲音訊。

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 結構中的音訊。

Python

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="lyria-3-clip-preview",
    input="Create a 30-second cheerful acoustic folk song with guitar and harmonica.",
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "audio":
                print(f"Generated audio with mime_type: {content_block.mime_type}")
                with open("music.mp3", "wb") as f:
                    f.write(base64.b64decode(content_block.data))
            elif content_block.type == "text":
                print(f"Lyrics: {content_block.text}")

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: 'Create a 30-second cheerful acoustic folk song with ' +
           'guitar and harmonica.',
});

for (const step of interaction.steps) {
    if (step.type === 'model_output') {
        for (const contentBlock of step.content) {
            if (contentBlock.type === 'audio') {
                console.log(`Generated audio with mime_type: ${contentBlock.mimeType}`);
                fs.writeFileSync('music.mp3', Buffer.from(contentBlock.data, 'base64'));
            } else if (contentBlock.type === 'text') {
                console.log(`Lyrics: ${contentBlock.text}`);
            }
        }
    }
}

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": "Create a 30-second cheerful acoustic folk song with guitar and harmonica."
}'

生成完整歌曲

使用 lyria-3-pro-preview 模型生成幾分鐘的完整歌曲。Pro 版模型可瞭解音樂結構，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-pro-preview",
    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-pro-preview',
    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.',
});

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-pro-preview",
    "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."
}'

選取輸出格式

根據預設，Lyria 3 模型會以 MP3 格式生成音訊。如果是 Lyria 3 Pro，您也可以設定 response_mime_type，要求以 WAV 格式輸出。

Python

interaction = client.interactions.create(
    model="lyria-3-pro-preview",
    input="An atmospheric ambient track.",
    response_modalities=["audio", "text"],
    response_mime_type="audio/wav",
)

JavaScript

const interaction = await client.interactions.create({
    model: 'lyria-3-pro-preview',
    input: 'An atmospheric ambient track.',
    responseModalities: ["audio", "text"],
    responseMimeType: "audio/wav",
});

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-pro-preview",
    "input": "An atmospheric ambient track.",
    "responseModalities": ["audio", "text"],
    "responseMimeType": "audio/wav"
  }'

剖析回應

Lyria 3 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

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);
}

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

根據圖片生成音樂

Lyria 3 支援多模態輸入內容，你可以在 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

uploaded_image = client.files.upload(file="desert_sunset.jpg")

response = client.interactions.create(
    model="lyria-3-pro-preview",
    input=[
        {"type": "text", "text": "An atmospheric ambient track inspired by the mood and colors in this image."},
        {
            "type": "image",
            "uri": uploaded_image.uri,
            "mime_type": uploaded_image.mime_type
        }
    ],
)

JavaScript

const uploadedImage = await client.files.upload({
    file: "desert_sunset.jpg",
    config: { mimeType: "image/jpeg" }
});

const interaction = await client.interactions.create({
    model: 'lyria-3-pro-preview',
    input: [
        { type: 'text', text: 'An atmospheric ambient track inspired by the mood and colors in this image.' },
        {
            type: 'image',
            uri: uploadedImage.uri,
            mimeType: uploadedImage.mimeType
        }
    ],
});

REST

# First upload the image using the Files API, then use the URI:
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-pro-preview",
    "input": [
      {"type": "text", "text": "An atmospheric ambient track inspired by the mood and colors in this image."},
      {"type": "image", "uri": "YOUR_FILE_URI", "mime_type": "image/jpeg"}
    ]
  }'

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-pro-preview",
    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-pro-preview',
    input: prompt,
});

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-pro-preview",
    "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，在歌曲的特定時間點指定要執行的動作。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-pro-preview",
    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-pro-preview',
    input: prompt,
});

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-pro-preview",
    "input": "[0:00 - 0:10] Intro: ..."
  }'

生成配樂

如要生成背景音樂、遊戲配樂或任何不需要人聲的音樂，可以提示模型生成純音樂曲目：

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.',
});

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 會根據提示的語言生成歌詞。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-pro-preview",
    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-pro-preview',
    input: 'Crée une chanson pop romantique en français sur un coucher de soleil à Paris. Utilise du piano et de la guitare acoustique.',
});

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-pro-preview",
    "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 會分析提示程序，根據提示透過音樂結構 (前奏、主歌、副歌、橋段等) 推理。這項程序會在生成音訊前執行，確保結構一致性和音樂性。

提示撰寫指南

提示越具體，結果就越符合需求。你可以加入以下內容，引導系統生成圖片：

  • 類型：指定類型或類型組合 (例如「lo-fi hip hop」、「jazz fusion」、「cinematic orchestral」)。
  • 樂器：指明樂器名稱 (例如「Fender Rhodes 鋼琴」、「滑音吉他」、「TR-808 鼓機」)。
  • BPM：設定節奏 (例如「120 BPM」、「70 BPM 左右的慢節奏」)。
  • 調性/音階：指定音樂調性 (例如「G 大調」、「D 小調」)。
  • 情緒和氛圍：使用描述性形容詞 (例如「懷舊」、「激進」、「空靈」、「夢幻」)。
  • 結構：使用 [Verse]、[Chorus]、[Bridge]、[Intro]、[Outro] 或時間戳記等標記，控制歌曲的進展。
  • 長度：短片模型一律會生成 30 秒的短片。如果是 Pro 模型，請在提示詞中指定預期長度 (例如「創作 2 分鐘的歌曲」)，或使用時間戳記控制長度。

提示詞範例

以下列舉幾個有效的提示：

  • "A 30-second lofi hip hop beat with dusty vinyl crackle, mellow Rhodes piano chords, a slow boom-bap drum pattern at 85 BPM, and a jazzy upright bass line. Instrumental only."
  • "An upbeat, feel-good pop song in G major at 120 BPM with bright acoustic guitar strumming, claps, and warm vocal harmonies about a summer road trip."
  • "A dark, atmospheric trap beat at 140 BPM with heavy 808 bass, eerie synth pads, sharp hi-hats, and a haunting vocal sample. In D minor."

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-pro-preview 生成完整長度的內容。
  • 提供清楚明確的說明，模糊不清的提示會產生一般結果。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] 標記可為模型提供明確的結構。
  • 歌詞和指示分開。提供自訂歌詞時，請清楚區隔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，不會影響聆聽體驗。
  • 多輪編輯：生成音樂是單輪程序。 目前版本的 Lyria 3 不支援透過多個提示詞，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，每次呼叫的結果也可能不同。

後續步驟