Criar um modelo personalizado

curl --request POST \
  --url https://api.apimart.ai/v1/music/generations/createModel \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "suno",
    "name": "warm folk model",
    "audio_urls": [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  }'

import requests

response = requests.post(
    "https://api.apimart.ai/v1/music/generations/createModel",
    headers={"Authorization": "Bearer <token>"},
    json={
        "model": "suno",
        "name": "warm folk model",
        "audio_urls": [
            "https://example.com/ref-01.mp3",
            "https://example.com/ref-02.mp3",
            "https://example.com/ref-03.wav",
            "https://example.com/ref-04.m4a",
            "https://example.com/ref-05.mp3",
            "https://example.com/ref-06.mp3",
        ],
    },
)
print(response.json())

const response = await fetch("https://api.apimart.ai/v1/music/generations/createModel", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "suno",
    name: "warm folk model",
    audio_urls: [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  })
});
console.log(await response.json());

{
  "code": 200,
  "data": [
    {"status": "submitted", "task_id": "task_01M24YMN4EV04M84R5QYM77R1E"}
  ]
}

{
  "code": 200,
  "data": {
    "id": "task_01M24YMN4EV04M84R5QYM77R1E",
    "status": "completed",
    "progress": 100,
    "result": {
      "model_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "warm folk music model"
    }
  }
}

POST

music

generations

createModel

curl --request POST \
  --url https://api.apimart.ai/v1/music/generations/createModel \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "suno",
    "name": "warm folk model",
    "audio_urls": [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  }'

import requests

response = requests.post(
    "https://api.apimart.ai/v1/music/generations/createModel",
    headers={"Authorization": "Bearer <token>"},
    json={
        "model": "suno",
        "name": "warm folk model",
        "audio_urls": [
            "https://example.com/ref-01.mp3",
            "https://example.com/ref-02.mp3",
            "https://example.com/ref-03.wav",
            "https://example.com/ref-04.m4a",
            "https://example.com/ref-05.mp3",
            "https://example.com/ref-06.mp3",
        ],
    },
)
print(response.json())

const response = await fetch("https://api.apimart.ai/v1/music/generations/createModel", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "suno",
    name: "warm folk model",
    audio_urls: [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  })
});
console.log(await response.json());

{
  "code": 200,
  "data": [
    {"status": "submitted", "task_id": "task_01M24YMN4EV04M84R5QYM77R1E"}
  ]
}

{
  "code": 200,
  "data": {
    "id": "task_01M24YMN4EV04M84R5QYM77R1E",
    "status": "completed",
    "progress": 100,
    "result": {
      "model_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "warm folk music model"
    }
  }
}

A criação do modelo é assíncrona. Consulte a tarefa com task_id e, ao concluir, leia o ID em data.result.model_id.

curl --request POST \
  --url https://api.apimart.ai/v1/music/generations/createModel \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "suno",
    "name": "warm folk model",
    "audio_urls": [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  }'

import requests

response = requests.post(
    "https://api.apimart.ai/v1/music/generations/createModel",
    headers={"Authorization": "Bearer <token>"},
    json={
        "model": "suno",
        "name": "warm folk model",
        "audio_urls": [
            "https://example.com/ref-01.mp3",
            "https://example.com/ref-02.mp3",
            "https://example.com/ref-03.wav",
            "https://example.com/ref-04.m4a",
            "https://example.com/ref-05.mp3",
            "https://example.com/ref-06.mp3",
        ],
    },
)
print(response.json())

const response = await fetch("https://api.apimart.ai/v1/music/generations/createModel", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "suno",
    name: "warm folk model",
    audio_urls: [
      "https://example.com/ref-01.mp3",
      "https://example.com/ref-02.mp3",
      "https://example.com/ref-03.wav",
      "https://example.com/ref-04.m4a",
      "https://example.com/ref-05.mp3",
      "https://example.com/ref-06.mp3"
    ]
  })
});
console.log(await response.json());

Authorizations

string

obrigatório

Bearer Token. Obtenha a chave na página de gerenciamento de chaves de API.

Body

string

padrão:"suno"

Use sempre suno.

string

obrigatório

Nome do modelo personalizado. Não pode ficar vazio após remover espaços no início e no fim.

string[]

obrigatório

De 6 a 24 URLs HTTP(S) diretas e públicas de áudio. MP3, WAV e M4A são recomendados. Cada URL deve retornar o arquivo diretamente, não uma página de login.

Um arquivo de mídia inválido pode fazer toda a criação do modelo falhar. Envie arquivos locais antes e use URLs públicas; não envie caminhos locais nem URLs blob:.

Response

integer

Código de status da resposta.

array

Resultado do envio. Leia data[0].task_id e consulte o status do treinamento com GET /v1/music/tasks/{task_id}.

{
  "code": 200,
  "data": [
    {"status": "submitted", "task_id": "task_01M24YMN4EV04M84R5QYM77R1E"}
  ]
}

{
  "code": 200,
  "data": {
    "id": "task_01M24YMN4EV04M84R5QYM77R1E",
    "status": "completed",
    "progress": 100,
    "result": {
      "model_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "warm folk music model"
    }
  }
}

Usar o modelo criado

Ao concluir, salve result.model_id. Use-o depois como custom_model_id e omita version e persona_id.

{
  "model": "suno",
  "custom_model_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "custom": true,
  "instrumental": false,
  "prompt": "[Verse]\nan old wooden guitar plays a new journey",
  "style": "acoustic folk, warm vocals",
  "max_mode": true,
  "audio_format": "mp3"
}

A criação pode levar vários minutos, até cerca de 20. A disponibilidade varia; não prometa expiração fixa. A criação e cada geração são cobradas separadamente.

Visão Geral

Modelos

Série de Texto

Série de Imagem

Série de Vídeo

Série de Áudio

Série de Moderação

Gerenciamento de Upload

Gerenciamento de Tarefas

Gerenciamento de Conta

Criar um modelo personalizado

Authorizations

Body

Response

Usar o modelo criado

​Authorizations

​Body

​Response

​Usar o modelo criado

Authorizations

Body

Response

Usar o modelo criado