Testen Sie das neue Gemini 3.1 Flash Live-Modell für die Audio-zu-Audio-Umwandlung in AI Studio.

Musik mit Lyria 3 generieren

Lyria 3 ist die Familie der Musikgenerierungsmodelle von Google, die über die Gemini API verfügbar sind. Mit Lyria 3 können Sie hochwertige 48-kHz-Stereo-Audiodateien aus Text-Prompts oder Bildern generieren. Diese Modelle liefern strukturelle Kohärenz, einschließlich Gesang, zeitgesteuerter Songtexte und vollständiger Instrumentalarrangements.

Die Lyria 3-Familie umfasst zwei Modelle:

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

Beide Modelle können mit der Standardmethode generateContent und der neuen Interactions API verwendet werden. Sie unterstützen multimodale Eingaben (Text und Bilder) und erzeugen 48-kHz-Stereo-Audio in Hi-Fi-Qualität.

Musikclip generieren

Das Modell Lyria 3 Clip generiert immer einen 30-sekündigen Clip. Rufen Sie zum Generieren eines Clips die generateContent Methode auf und legen Sie response_modalities auf ["AUDIO", "TEXT"] fest. Wenn Sie TEXT einbeziehen, erhalten Sie neben der Audiodatei auch den generierten Songtext oder die Songstruktur.

Python

from google import genai
from google.genai import types

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.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

# 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.",
    config: {
      responseModalities: ["AUDIO", "TEXT"],
    },
  });

  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)
    }

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

    result, err := client.Models.GenerateContent(
        ctx,
        "lyria-3-clip-preview",
        genai.Text("Create a 30-second cheerful acoustic folk song " +
                   "with guitar and harmonica."),
        config,
    )
    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.GenerateContentConfig;
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()) {
      GenerateContentConfig config = GenerateContentConfig.builder()
          .responseModalities("AUDIO", "TEXT")
          .build();

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

      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."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

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 config = new GenerateContentConfig {
      ResponseModalities = { "AUDIO", "TEXT" }
    };

    var response = await client.Models.GenerateContentAsync(
      model: "lyria-3-clip-preview",
      contents: "Create a 30-second cheerful acoustic folk song with guitar and harmonica.",
      config: config
    );

    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-pro-preview können Sie Songs in voller Länge generieren, die ein paar Minuten dauern. Das Pro-Modell versteht die musikalische Struktur 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-Minuten-Song“) oder Zeitstempel verwenden, um die Struktur zu definieren.

Python

response = client.models.generate_content(
    model="lyria-3-pro-preview",
    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.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

JavaScript

const response = await ai.models.generateContent({
  model: "lyria-3-pro-preview",
  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.",
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

Ok

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3-pro-preview",
    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."),
    config,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3-pro-preview",
    "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.",
    config);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-pro-preview: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."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3-pro-preview",
  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.",
  config: config
);

Antwort analysieren

Die Antwort von Lyria 3 besteht aus mehreren Teilen. Textteile enthalten den generierten Songtext oder eine JSON-Beschreibung der Songstruktur. Teile mit inline_data enthalten die Audiobytes.

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 unterstützt multimodale Eingaben. Sie können neben Ihrem Text-Prompt bis zu 10 Bilder angeben. 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-pro-preview",
    contents=[
        "An atmospheric ambient track inspired by the mood and "
        "colors in this image.",
        image,
    ],
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

JavaScript

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

const response = await ai.models.generateContent({
  model: "lyria-3-pro-preview",
  contents: [
    { text: "An atmospheric ambient track inspired by the mood " +
            "and colors in this image." },
    {
      inlineData: {
        mimeType: "image/jpeg",
        data: base64Image,
      },
    },
  ],
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

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-pro-preview",
    contents,
    config,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3-pro-preview",
    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")),
    config);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-pro-preview: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>\"
            }
          }
      ]
    }],
    \"generationConfig\": {
      \"responseModalities\": [\"AUDIO\", \"TEXT\"]
    }
  }"

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3-pro-preview",
  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")
  },
  config: config
);

Benutzerdefinierten Songtext angeben

Sie können Ihren eigenen Songtext schreiben und ihn in den Prompt einfügen. Verwenden Sie Abschnitts-Tags wie [Verse], [Chorus] und [Bridge], damit das Modell die Songstruktur 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-pro-preview",
    contents=prompt,
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

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-pro-preview",
  contents: prompt,
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

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-pro-preview",
    genai.Text(prompt),
    config,
)

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-pro-preview",
    prompt,
    config);

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-pro-preview",
  contents: prompt,
  config: config
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-pro-preview: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: ..."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

Timing und Struktur steuern

Mit Zeitstempeln können Sie genau angeben, was zu bestimmten Zeitpunkten im Song passiert. Das ist nützlich, um zu steuern, wann Instrumente einsetzen, wann der Songtext gesungen wird und wie der Song weitergeht:

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-pro-preview",
    contents=prompt,
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

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-pro-preview",
  contents: prompt,
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

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-pro-preview",
    genai.Text(prompt),
    config,
)

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-pro-preview",
    prompt,
    config);

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-pro-preview",
  contents: prompt,
  config: config
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-pro-preview:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "[0:00 - 0:10] Intro: ..."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

Instrumentaltracks generieren

Für Hintergrundmusik, Game-Soundtracks oder jeden Anwendungsfall, bei dem kein Gesang erforderlich ist, können Sie das Modell auffordern, reine Instrumentaltracks 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.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

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.",
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

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."),
    config,
)

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.",
    config);

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.",
  config: config
);

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."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

Musik in verschiedenen Sprachen generieren

Lyria 3 generiert Songtexte in der Sprache Ihres Prompts. Wenn Sie einen Song mit französischem Songtext 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-pro-preview",
    contents="Crée une chanson pop romantique en français sur un "
             "coucher de soleil à Paris. Utilise du piano et de "
             "la guitare acoustique.",
    config=types.GenerateContentConfig(
        response_modalities=["AUDIO", "TEXT"],
    ),
)

JavaScript

const response = await ai.models.generateContent({
  model: "lyria-3-pro-preview",
  contents: "Crée une chanson pop romantique en français sur un " +
            "coucher de soleil à Paris. Utilise du piano et de " +
            "la guitare acoustique.",
  config: {
    responseModalities: ["AUDIO", "TEXT"],
  },
});

Ok

result, err := client.Models.GenerateContent(
    ctx,
    "lyria-3-pro-preview",
    genai.Text("Crée une chanson pop romantique en français sur un " +
               "coucher de soleil à Paris. Utilise du piano et de " +
               "la guitare acoustique."),
    config,
)

Java

GenerateContentResponse response = client.models.generateContent(
    "lyria-3-pro-preview",
    "Crée une chanson pop romantique en français sur un "
        + "coucher de soleil à Paris. Utilise du piano et de "
        + "la guitare acoustique.",
    config);

C#

var response = await client.Models.GenerateContentAsync(
  model: "lyria-3-pro-preview",
  contents: "Crée une chanson pop romantique en français sur un " +
            "coucher de soleil à Paris. Utilise du piano et de " +
            "la guitare acoustique.",
  config: config
);

REST

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/lyria-3-pro-preview: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."}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO", "TEXT"]
    }
  }'

Modellintelligenz

Lyria 3 analysiert Ihren Prompt-Prozess, bei dem das Modell die musikalische Struktur (Intro, Strophe, Refrain, Bridge usw.) anhand Ihres Prompts ableitet. Dies geschieht, bevor die Audiodatei generiert wird, und sorgt für strukturelle Kohärenz und Musikalität.

Interactions API

Sie können Lyria 3-Modelle mit der Interactions API verwenden; einer einheitlichen Benutzeroberfläche für die Interaktion mit Gemini-Modellen und -Agents. Sie vereinfacht die Statusverwaltung und langwierige Aufgaben für komplexe multimodale Anwendungsfälle.

Python

from google import genai

client = genai.Client()

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.",
    response_modalities=["AUDIO", "TEXT"]
)

for output in interaction.outputs:
    if output.text:
        print(output.text)
    elif output.inline_data:
         with open("interaction_output.mp3", "wb") as f:
            f.write(output.inline_data.data)
         print("Audio saved to interaction_output.mp3")

JavaScript

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

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.',
  responseModalities: ['AUDIO', 'TEXT'],
});

for (const output of interaction.outputs) {
  if (output.text) {
    console.log(output.text);
  } else if (output.inlineData) {
    const buffer = Buffer.from(output.inlineData.data, 'base64');
    fs.writeFileSync('interaction_output.mp3', buffer);
    console.log('Audio saved to interaction_output.mp3');
  }
}

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.",
    "responseModalities": ["AUDIO", "TEXT"]
}'

Anleitung zu Prompts

Je genauer Ihr Prompt ist, desto besser sind die Ergebnisse. Sie können Folgendes einbeziehen, um die Generierung zu steuern:

Genre: Geben Sie ein Genre oder eine Mischung aus Genres an (z.B. „Lo-Fi-Hip-Hop“, „Jazz Fusion“, „Orchestral-Soundtrack“).
Instrumente: Nennen Sie bestimmte Instrumente (z.B. „Fender Rhodes-Piano“, „Slide-Gitarre“, „TR-808-Drum-Machine“).
BPM: Legen Sie das Tempo fest (z.B. „120 BPM“, „langsames Tempo um 70 BPM“).
Tonart/Tonleiter: Geben Sie eine Tonart an (z.B. „in G-Dur“, „D-Moll“).
Stimmung und Atmosphäre: Verwenden Sie beschreibende Adjektive (z.B. „nostalgisch“, „aggressiv“, „ätherisch“, „vertäumt“).
Struktur: Verwenden Sie Tags wie [Verse], [Chorus], [Bridge], [Intro], [Outro] oder Zeitstempel, um den Ablauf des Songs zu steuern.
Dauer: Das Modell „Clip“ erzeugt immer 30-sekündige Clips. Geben Sie für das Modell „Pro“ die gewünschte Länge in Ihrem Prompt an (z.B. „Erstelle einen 2-Minuten-Song“) oder verwenden Sie Zeitstempel, um die Dauer zu steuern.

Beispiele für Prompts

Beispiele für effektive Prompts:

"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."

Best Practices

Zuerst mit „Clip“ iterieren Verwenden Sie das schnellere Modell lyria-3-clip-preview, um mit Prompts zu experimentieren, bevor Sie mit lyria-3-pro-preview einen Song in voller Länge generieren.
Machen Sie genaue Angaben Vage Prompts führen zu allgemeinen Ergebnissen. Geben Sie Instrumente, BPM, Tonart, Stimmung und Struktur an, um die besten Ergebnisse zu erzielen.
Passen Sie die Sprache an Verwenden Sie die Sprache, in der Sie den Songtext haben möchten.
Abschnitts-Tags verwenden Die Tags [Verse], [Chorus] und [Bridge] geben dem Modell eine klare Struktur, an die es sich halten kann.
Songtext von Anweisungen trennen Wenn Sie einen benutzerdefinierten Songtext angeben, trennen Sie ihn deutlich von Ihren 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 Songtexte generiert werden sollen.
Wasserzeichen: Alle generierten Audiodateien enthalten ein SynthID-Audio-Wasserzeichen zur Identifizierung. Dieses Wasserzeichen ist für das menschliche Ohr nicht wahrnehmbar und beeinträchtigt das Hörerlebnis nicht.
Bearbeitung in mehreren Schritten: Die Musikgenerierung ist ein einmaliger Vorgang. Die iterative Bearbeitung oder Verfeinerung eines generierten Clips durch mehrere Prompts wird in der aktuellen Version von Lyria 3 nicht unterstützt.
Länge: Das Modell „Clip“ erzeugt immer 30-sekündige Clips. Das Modell „Pro“ generiert Songs, die ein paar Minuten dauern. Die genaue Dauer kann durch Ihren Prompt beeinflusst werden.
Determinismus: Die Ergebnisse können zwischen den Aufrufen variieren, auch bei demselben Prompt.

Nächste Schritte

Preise für Lyria 3-Modelle ansehen
Musik in Echtzeit mit Lyria RealTime generieren
Unterhaltungen mit mehreren Sprechern mit den TTS-Modellen generieren
Bilderoder Videosgenerieren
Audio-Dateien mit Gemini verstehen
Unterhaltungen mit Gemini in Echtzeit über die Live API