Générer de la musique avec Lyria

Vous pouvez utiliser Lyria pour générer de nouveaux morceaux de musique à partir de prompts. Les interfaces compatibles incluent la Cloud de Confiance consoleet l'API Gemini API.

Essayer Lyria sur Agent Platform (Agent Platform Studio)

Avant de commencer

1. In the Cloud de Confiance console, on the project selector page, select or create a Cloud de Confiance project.

   Roles required to select or create a project

   • Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
   • Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

   Go to project selector

2. Enable the Gemini Enterprise Agent Platform API, if it is not already enabled.

   Roles required to enable APIs

   To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

   Enable the API

3. Configurez l'authentification pour votre environnement.

   Sélectionnez l'onglet correspondant à la façon dont vous prévoyez d'utiliser les exemples de cette page :

   Console

   Lorsque vous utilisez la Cloud de Confiance console pour accéder aux Cloud de Confiance by S3NS services et aux API, vous n'avez pas besoin de configurer l'authentification.

   REST

   Pour utiliser les exemples API REST de cette page dans un environnement de développement local, vous devez utiliser les identifiants que vous fournissez à la gcloud CLI.

   Installez la Google Cloud CLI, puis connectez-vous à la gcloud CLI avec votre identité fédérée.

   Pour en savoir plus, consultez la section S'authentifier pour utiliser REST dans la documentation sur l' Cloud de Confiance authentification.

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions

{
  "model": "MODEL_ID",
  "input": [
    {
      "type": "text",
      "text": "TEXT_PROMPT"
    },
    {
      "type": "image",
      "mime_type": "image/jpeg",
      "uri": "IMAGE_URI"
    },
    {
      "type": "image",
      "mime_type": "image/png",
      "data": "IMAGE_DATABYTES"
    },
  ]
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/interactions" | Select-Object -Expand Content

{
  "status": "completed",
  "outputs": [
    {
      "text": "LYRICS",
      "type": "text"
    },
    {
      "text": "DESCRIPTION",
      "type": "text"
    },
    {
      "mime_type": "audio/mpeg",
      "data": "GENERATED_SONG_DATABYTES",
      "type": "audio"
    },
    {}
  ],
  "role": "model",
  "created": "CREATED_TIME",
  "updated": "UPDATE_TIME",
  "object": "interaction",
  "model": "lyria-3-pro-preview"
}

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/lyria-002:predict \
  -d '{
    "instances": [
      {
        "prompt": "An uplifting and hopeful orchestral piece with a soaring string melody and triumphant brass.",
        "negative_prompt": " dissonant, minor key",
        "seed": 12345
      }
    ],
    "parameters": {
      // "sample_count": 1 // Use either seed or sample_count
    }
  }'

{
  "predictions": [
    {
      "audioContent": "BASE64_ENCODED_WAV_STRING_SAMPLE_1",
      "mimeType": "audio/wav"
    },
    {
      "audioContent": "BASE64_ENCODED_WAV_STRING_SAMPLE_2",
      "mimeType": "audio/wav"
    }
  ],
  "deployedModelId": "xxxxxxxxxxxxxxx",
  "model": "projects/PROJECT_ID/locations/LOCATION/publishers/google/models/lyria-002",
  "modelDisplayName": "Lyria 2"
}

Étape suivante

• Découvrez comment rédiger des prompts efficaces dans le guide sur les prompts de génération de musique Lyria.

• Consultez la documentation de référence de l'API Lyria.

• Découvrez d'autres modèles d'IA générative sur Gemini Enterprise Agent Platform.