Musik mit Lyria 3.5 generieren

Lyria 3.5 ist eine Familie von Modellen zur Musikgenerierung von Google, die über die Gemini API verfügbar ist. Mit Lyria 3.5 können Sie aus Text-Prompts oder Bildern hochwertiges Stereo-Audio mit 44,1 kHz generieren. Diese Modelle liefern strukturelle Kohärenz, einschließlich Gesang, zeitgesteuerter Songtexte und vollständiger Instrumentalarrangements.

Die Lyria-Familie umfasst folgende Modelle:

Modell Modell-ID Optimal für Dauer Ausgabe
Lyria 3 Clip lyria-3-clip-preview Kurze Clips, Loops, Vorschauen 30 Sekunden MP3
Lyria 3.5 lyria-3.5 Songs in voller Länge mit Strophen, Refrains und Bridges Ein paar Minuten (über Prompt steuerbar) MP3

Beide Modelle können mit der Standardmethode generateContent und der neuen Interactions API verwendet werden.Sie unterstützen multimodale Eingaben (Text und Bilder) und erzeugen Stereo-Audio mit 44,1 kHz.

Musikclip erstellen

Das Modell „Lyria 3 Clip“ generiert immer einen 30‑sekündigen Clip. Rufen Sie die Methode generateContent mit einem Text-Prompt auf, um einen Clip zu generieren. Die Antwort enthält immer den generierten Text und die Songstruktur sowie das Audio.

Python

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="lyria-3-clip-preview",
    contents="Create a 30-second cheerful acoustic folk song with "
             "guitar and harmonica.",
)

# Parse the response
for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        with open("clip.mp3", "wb") as f:
            f.write(part.inline_data.data)
        print("Audio saved to clip.mp3")

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const ai = new GoogleGenAI({});

async function main() {
  const response = await ai.models.generateContent({
    model: "lyria-3-clip-preview",
    contents: "Create a 30-second cheerful acoustic folk song with " +
              "guitar and harmonica.",

  });

  for (const part of response.candidates[0].content.parts) {
    if (part.text) {
      console.log(part.text);
    } else if (part.inlineData) {
      const buffer = Buffer.from(part.inlineData.data, "base64");
      fs.writeFileSync("clip.mp3", buffer);
      console.log("Audio saved to clip.mp3");
    }
  }
}

main();

Ok

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    result, err := client.Models.GenerateContent(
        ctx,
        "lyria-3-clip-preview",
        genai.Text("Create a 30-second cheerful acoustic folk song " +
                   "with guitar and harmonica."),
        nil,
    )
    if err != nil {
        log.Fatal(err)
    }

    for _, part := range result.Candidates[0].Content.Parts {
        if part.Text != "" {
            fmt.Println(part.Text)
        } else if part.InlineData != nil {
            err := os.WriteFile("clip.mp3", part.InlineData.Data, 0644)
            if err != nil {
                log.Fatal(err)
            }
            fmt.Println("Audio saved to clip.mp3")
        }
    }
}

Java

import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.Part;

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

public class GenerateMusicClip {
  public static void main(String[] args) throws IOException {

    try (Client client = new Client()) {
      GenerateContentResponse response = client.models.generateContent(
          "lyria-3-clip-preview",
          "Create a 30-second cheerful acoustic folk song with "
              + "guitar and harmonica.");

      for (Part part : response.parts()) {
        if (part.text().isPresent()) {
          System.out.println(part.text().get());
        } else if (part.inlineData().isPresent()) {
          var blob = part.inlineData().get();
          if (blob.data().isPresent()) {
            Files.write(Paths.get("clip.mp3"), blob.data().get());
            System.out.println("Audio saved to clip.mp3");
          }
        }
      }
    }
  }
}

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-clip-preview:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "Create a 30-second cheerful acoustic folk song with guitar and harmonica."}
      ]
    }]
  }'

C#

using System.Threading.Tasks;
using Google.GenAI;
using Google.GenAI.Types;
using System.IO;

public class GenerateMusicClip {
  public static async Task main() {
    var client = new Client();
    var response = await client.Models.GenerateContentAsync(
      model: "lyria-3-clip-preview",
      contents: "Create a 30-second cheerful acoustic folk song with guitar and harmonica."
    );

    foreach (var part in response.Candidates[0].Content.Parts) {
      if (part.Text != null) {
        Console.WriteLine(part.Text);
      } else if (part.InlineData != null) {
        await File.WriteAllBytesAsync("clip.mp3", part.InlineData.Data);
        Console.WriteLine("Audio saved to clip.mp3");
      }
    }
  }
}

Song in voller Länge generieren

Mit dem Modell lyria-3.5 können Sie Songs in voller Länge generieren, die einige Minuten dauern. Das Pro-Modell versteht musikalische Strukturen und kann Kompositionen mit unterschiedlichen Strophen, Refrains und Bridges erstellen. Sie können die Dauer beeinflussen, indem Sie sie in Ihrem Prompt angeben (z.B. „Erstelle einen 2-minütigen Song“) oder indem Sie Zeitstempel verwenden, um die Struktur zu definieren.

Python

response = client.models.generate_content(
    model="lyria-3.5",
    contents="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 response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: "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.",

});

Ok

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    genai.Text("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."),
    nil,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    "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 -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3.5:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "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."}
      ]
    }]
  }'

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: "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."
);

Ausgabeformat auswählen

Standardmäßig generieren die Lyria 3.5-Modelle Audio im MP3-Format. Bei Lyria 3.5 können Sie die Ausgabe auch im WAV-Format anfordern, indem Sie response_format in generationConfig festlegen.

Python

from google.genai import types

response = client.models.generate_content(
    model="lyria-3.5",
    contents="An atmospheric ambient track.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
        response_format={"audio": {"mime_type": "audio/wav"}},
    ),
)

JavaScript

const response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: "An atmospheric ambient track.",
  config: {
    responseModalities: ["AUDIO", "TEXT"],
    responseFormat: { audio: { mimeType: "audio/wav" } },
  },
});

Ok

config := &genai.GenerateContentConfig{
    ResponseModalities: []string{"AUDIO", "TEXT"},
    ResponseMIMEType:   "audio/wav",
}

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    genai.Text("An atmospheric ambient track."),
    config,
)

Java

GenerateContentConfig config = GenerateContentConfig.builder()
    .responseModalities("AUDIO", "TEXT")
    .responseFormat(ResponseFormat.builder().audio(AudioFormat.builder().mimeType("audio/wav").build()).build())
    .build();

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    "An atmospheric ambient track.",
    config);

C#

var config = new GenerateContentConfig {
  ResponseModalities = { "AUDIO", "TEXT" },
  ResponseMimeType = "audio/wav"
};

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: "An atmospheric ambient track.",
  config: config
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3.5:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "An atmospheric ambient track."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"],
      "responseFormat": { "audio": { "mimeType": "audio/wav" } }
    }
  }'

Antwort analysieren

Die Antwort von Lyria 3.5 besteht aus mehreren Teilen. Textteile enthalten den generierten Songtext oder eine JSON-Beschreibung der Songstruktur. Teile mit inline_data enthalten die Audio-Bytes.

Python

lyrics = []
audio_data = None

for part in response.parts:
    if part.text is not None:
        lyrics.append(part.text)
    elif part.inline_data is not None:
        audio_data = part.inline_data.data

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 part of response.candidates[0].content.parts) {
  if (part.text) {
    lyrics.push(part.text);
  } else if (part.inlineData) {
    audioData = Buffer.from(part.inlineData.data, "base64");
  }
}

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

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

Ok

var lyrics []string
var audioData []byte

for _, part := range result.Candidates[0].Content.Parts {
    if part.Text != "" {
        lyrics = append(lyrics, part.Text)
    } else if part.InlineData != nil {
        audioData = part.InlineData.Data
    }
}

if len(lyrics) > 0 {
    fmt.Println("Lyrics:\n" + strings.Join(lyrics, "\n"))
}

if audioData != nil {
    err := os.WriteFile("output.mp3", audioData, 0644)
    if err != nil {
        log.Fatal(err)
    }
}

Java

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

for (Part part : response.parts()) {
  if (part.text().isPresent()) {
    lyrics.add(part.text().get());
  } else if (part.inlineData().isPresent()) {
    audioData = part.inlineData().get().data().get();
  }
}

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

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

C#

var lyrics = new List<string>();
byte[] audioData = null;

foreach (var part in response.Candidates[0].Content.Parts) {
  if (part.Text != null) {
    lyrics.Add(part.Text);
  } else if (part.InlineData != null) {
    audioData = part.InlineData.Data;
  }
}

if (lyrics.Count > 0) {
  Console.WriteLine("Lyrics:\n" + string.Join("\n", lyrics));
}

if (audioData != null) {
  await File.WriteAllBytesAsync("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 '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | base64 -d > output.mp3

Musik aus Bildern generieren

Lyria 3.5 unterstützt multimodale Eingaben. Sie können Ihrem Textprompt bis zu 10 Bilder hinzufügen. Das Modell komponiert dann Musik, die von den visuellen Inhalten inspiriert ist.

Python

from PIL import Image

image = Image.open("desert_sunset.jpg")

response = client.models.generate_content(
    model="lyria-3.5",
    contents=[
        "An atmospheric ambient track inspired by the mood and "
        "colors in this image.",
        image,
    ],
)

JavaScript

const imageData = fs.readFileSync("desert_sunset.jpg");
const base64Image = imageData.toString("base64");

const response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: [
    { text: "An atmospheric ambient track inspired by the mood " +
            "and colors in this image." },
    {
      inlineData: {
        mimeType: "image/jpeg",
        data: base64Image,
      },
    },
  ],

});

Ok

imgData, err := os.ReadFile("desert_sunset.jpg")
if err != nil {
    log.Fatal(err)
}

parts := []*genai.Part{
    genai.NewPartFromText("An atmospheric ambient track inspired " +
        "by the mood and colors in this image."),
    &genai.Part{
        InlineData: &genai.Blob{
            MIMEType: "image/jpeg",
            Data:     imgData,
        },
    },
}

contents := []*genai.Content{
    genai.NewContentFromParts(parts, genai.RoleUser),
}

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    contents,
    nil,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    Content.fromParts(
        Part.fromText("An atmospheric ambient track inspired by "
            + "the mood and colors in this image."),
        Part.fromBytes(
            Files.readAllBytes(Path.of("desert_sunset.jpg")),
            "image/jpeg")));

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3.5:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"contents\": [{
      \"parts\":[
          {\"text\": \"An atmospheric ambient track inspired by the mood and colors in this image.\"},
          {
            \"inline_data\": {
              \"mime_type\":\"image/jpeg\",
              \"data\": \"<BASE64_IMAGE_DATA>\"
            }
          }
      ]
    }]
  }"

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: new List<Part> {
    Part.FromText("An atmospheric ambient track inspired by the mood and colors in this image."),
    Part.FromBytes(await File.ReadAllBytesAsync("desert_sunset.jpg"), "image/jpeg")
  }
);

Benutzerdefinierten Songtext angeben

Sie können Ihren eigenen Songtext schreiben und in den Prompt einfügen. Verwende Abschnitts-Tags wie [Verse], [Chorus] und [Bridge], damit das Modell die Songstruktur besser versteht:

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.
"""

response = client.models.generate_content(
    model="lyria-3.5",
    contents=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 response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: prompt,

});

Ok

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.
`

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    genai.Text(prompt),
    nil,
)

Java

String 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.
    """;

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    prompt);

C#

var 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.
";

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: prompt
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3.5:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "Create a dreamy indie pop song with the following lyrics: ..."}
      ]
    }]
  }'

Zeit und Struktur steuern

Mit Zeitstempeln kannst du genau angeben, was zu bestimmten Zeitpunkten im Song passieren soll. Das ist nützlich, um zu steuern, wann Instrumente einsetzen, wann der Text gesprochen wird und wie sich der Song entwickelt:

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.
"""

response = client.models.generate_content(
    model="lyria-3.5",
    contents=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 response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: prompt,

});

Ok

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.
`

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    genai.Text(prompt),
    nil,
)

Java

String 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.
    """;

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    prompt);

C#

var 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.
";

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: prompt
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3.5:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "[0:00 - 0:10] Intro: ..."}
      ]
    }]
  }'

Instrumental-Tracks generieren

Für Hintergrundmusik, Game-Soundtracks oder jeden Anwendungsfall, in dem kein Gesang erforderlich ist, können Sie das Modell auffordern, nur Instrumental-Tracks zu erstellen:

Python

response = client.models.generate_content(
    model="lyria-3-clip-preview",
    contents="A bright chiptune melody in C Major, retro 8-bit "
             "video game style. Instrumental only, no vocals.",
)

JavaScript

const response = await ai.models.generateContent({
  model: "lyria-3-clip-preview",
  contents: "A bright chiptune melody in C Major, retro 8-bit " +
            "video game style. Instrumental only, no vocals.",

});

Ok

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3-clip-preview",
    genai.Text("A bright chiptune melody in C Major, retro 8-bit " +
               "video game style. Instrumental only, no vocals."),
    nil,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3-clip-preview",
    "A bright chiptune melody in C Major, retro 8-bit "
        + "video game style. Instrumental only, no vocals.");

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3-clip-preview",
  contents: "A bright chiptune melody in C Major, retro 8-bit " +
            "video game style. Instrumental only, no vocals."
);

REST

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

Musik in verschiedenen Sprachen generieren

Lyria 3.5 generiert Songtexte in der Sprache Ihres Prompts. Wenn Sie einen Song mit französischen Texten generieren möchten, schreiben Sie Ihren Prompt auf Französisch. Das Modell passt seinen Gesangsstil und seine Aussprache an die Sprache an.

Python

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

JavaScript

const response = await ai.models.generateContent({
  model: "lyria-3.5",
  contents: "Crée une chanson pop romantique en français sur un " +
            "coucher de soleil à Paris. Utilise du piano et de " +
            "la guitare acoustique.",

});

Ok

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3.5",
    genai.Text("Crée une chanson pop romantique en français sur un " +
               "coucher de soleil à Paris. Utilise du piano et de " +
               "la guitare acoustique."),
    nil,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3.5",
    "Crée une chanson pop romantique en français sur un "
        + "coucher de soleil à Paris. Utilise du piano et de "
        + "la guitare acoustique.");

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3.5",
  contents: "Crée une chanson pop romantique en français sur un " +
            "coucher de soleil à Paris. Utilise du piano et de " +
            "la guitare acoustique."
);

REST

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

Modellintelligenz

Lyria 3.5 analysiert Ihren Prompt-Prozess, wobei das Modell anhand Ihres Prompts die musikalische Struktur (Intro, Strophe, Refrain, Bridge usw.) ableitet. Das geschieht, bevor das Audio generiert wird, und sorgt für strukturelle Kohärenz und Musikalität.

Interactions API

Sie können Lyria 3.5-Modelle mit der Interactions API verwenden, einer einheitlichen Schnittstelle für die Interaktion mit Gemini-Modellen und ‑Agents. Dadurch werden die Statusverwaltung und die Ausführung zeitaufwendiger Aufgaben für komplexe multimodale Anwendungsfälle vereinfacht.

Python

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="lyria-3.5",
    input="A melancholic jazz fusion track in D minor, " +
          "featuring a smooth saxophone melody, walking bass line, " +
          "and complex drum rhythms.",
)

generated_audio = interaction.output_audio
if generated_audio:
    with open("interaction_output.mp3", "wb") as f:
        f.write(base64.b64decode(generated_audio.data))
    print("Audio saved to interaction_output.mp3")

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-3.5',
  input: 'A melancholic jazz fusion track in D minor, ' +
         'featuring a smooth saxophone melody, walking bass line, ' +
         'and complex drum rhythms.',
});

const generatedAudio = interaction.output_audio;
if (generatedAudio) {
  fs.writeFileSync('interaction_output.mp3', Buffer.from(generatedAudio.data, 'base64'));
  console.log('Audio saved to interaction_output.mp3');
}

const lyrics = interaction.output_text;
if (lyrics) {
  console.log(`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-3.5",
    "input": "A melancholic jazz fusion track in D minor, featuring a smooth saxophone melody, walking bass line, and complex drum rhythms."
}'

Leitfaden für Prompts

Informationen zum Erstellen effektiver Prompts für Musikgenres, Instrumente, Songstruktur, benutzerdefinierte Texte und Gesangsstile finden Sie im Leitfaden für Prompts für Lyria.

Best Practices

  • Erst mit Clip iterieren: Mit dem schnelleren Modell lyria-3-clip-preview können Sie mit Prompts experimentieren, bevor Sie eine vollständige Generierung mit lyria-3.5 starten.
  • Beschreiben Sie das Angebot möglichst genau. Vage Prompts führen zu allgemeinen Ergebnissen. Geben Sie Instrumente, BPM, Tonart, Stimmung und Struktur an, um das beste Ergebnis zu erzielen.
  • Sprache anpassen: Geben Sie den Prompt in der Sprache ein, in der Sie den Text haben möchten.
  • Abschnittstags verwenden: Die Tags [Verse], [Chorus] und [Bridge] geben dem Modell eine klare Struktur vor.
  • Songtexte von Anweisungen trennen: Wenn Sie benutzerdefinierte Liedtexte angeben, trennen Sie diese deutlich von den Anweisungen zur musikalischen Ausrichtung.

Beschränkungen

  • Sicherheit: Alle Prompts werden von Sicherheitsfiltern geprüft. Prompts, die die Filter auslösen, werden blockiert. Dazu gehören Prompts, in denen bestimmte Künstlerstimmen angefordert werden oder urheberrechtlich geschützte Texte generiert werden sollen.
  • Wasserzeichen: Alle generierten Audioinhalte enthalten ein SynthID-Audio-Wasserzeichen zur Identifizierung. Dieses Wasserzeichen ist für das menschliche Ohr nicht wahrnehmbar und hat keine Auswirkungen auf das Hörerlebnis.
  • Bearbeitung in mehreren Schritten: Die Musikgenerierung ist ein Prozess in einem Schritt. Das iterative Bearbeiten oder Verfeinern eines generierten Clips durch mehrere Prompts wird in der aktuellen Version von Lyria 3.5 nicht unterstützt.
  • Länge: Das Clip-Modell generiert immer 30-sekündige Clips. Das Pro-Modell generiert Songs, die einige Minuten lang sind. Die genaue Dauer kann durch Ihren Prompt beeinflusst werden.
  • Determinismus: Die Ergebnisse können zwischen den Aufrufen variieren, auch wenn derselbe Prompt verwendet wird.

Nächste Schritte