Skip to main content

​
Generate AI Singing from Lyrics

  • This endpoint generates AI singing from provided lyrics using AI models.

​
Core Parameters

The parameters below define the request body for this API.
ParameterTypeRequired?Description
lyricsstring✅ RequiredThe lyrics to be sung by the AI-generated singing.
styleOfMusicstring⚠️ OptionalPreferred style. Select one from supported styles listed below.
audioUrlstring⚠️ OptionalURL to a reference audio file for musical influence.
The audio URL must contain only singing vocals without background music. If audioUrl is provided, styleOfMusic will be ignored.

​
Supported Music Styles

The styleOfMusic parameter can be one of the following values:
  • Pop(Female)
  • Pop(Male)
  • Rap
  • Hiphop
  • Vocal Chops
  • Hyperpop (Female)
  • Meow Meow Cat
  • Rock
  • Kawaii
  • Hard Rock
  • Metal
  • Vocoder
  • ASMR Singing
  • Choir
  • Orchestral Choir
  • Gregorian Chant
  • Ancient Chant
  • Spoken Word
  • Voicemail (Male)
  • Voicemail (Female)
  • Cute Kkey
  • Ghost Whispering
  • Group People Whispering
  • Mongolian Throat Singing

​
Request Body

{
  "lyrics": "string",
  "styleOfMusic": "string",
  "audioUrl": "string"
}

​
Code Samples

  • Python
  • cURL
  • JavaScript
  import requests

  url = "https://api.soundverse.ai/v2/generate/ai-singing-gen"
  headers = {
      "Authorization": "Bearer your_api_key_here",
      "Content-Type": "application/json"
  }
  payload = {
      "lyrics": "Verse 1: Walking down the street, feeling the beat...",
      "styleOfMusic": "Pop",
      "audioUrl": "optional"
  }

  response = requests.post(url, json=payload, headers=headers)
  print(response.json())

​
Response

  • 200 OK
  • 500 Internal Server Error
  • 504 Gateway Timeout
{
  "messageId": "string",
  "prompt": "string",
  "albumArt": "string",
  "aiReply": "string",
  "audioData": [
    {
      "audioUrl": "string",
      "songName": "string",
      "licenses": {
        "licenses": "string"
      }
    }
  ]
}

​
Response Fields

FieldTypeDescription
messageIdstringUnique identifier for the generation request.
promptstringThe processed prompt used for generation.
albumArtstringURL to the generated album artwork.
aiReplystringAI-generated message about the creation.
audioDataarrayArray containing the generated audio file(s).
└─ audioUrlstringDirect URL to download/stream the generated audio.
└─ songNamestringName/title of the generated song.
└─ licensesobjectLicensing information for the generated content.

​
Sample Output

{
  "messageId": "68f28481ce60695f903644b8",
  "prompt": "La la la, singing in the rain, feeling happy and free",
  "albumArt": "https://storage.soundverse.ai/soundverse-album-art/681babcdc9b9a92b09132ff5/681babcdc9b9a92b09132ff5/20251017180149_00000_album_cover_art_for_La_la_la_singing_in_the_rain_feeling_happy_and_free.png",
  "aiReply": "The digital canvas has come alive with your audio masterpiece. It beckons you to listen, explore, and be inspired.",
  "audioData": [
    {
      "audioUrl": "https://storage.soundverse.ai/x-one/681babcdc9b9a92b09132ff5/681babcdc9b9a92b09132ff5/tmpsyokfwlm.mp3",
      "songName": "Raindrop Serenade: Melodies of Joyful Liberation",
      "licenses": {
        "licenses": "Royalty-Free"
      }
    }
  ]
}

​
Possible Errors :

  • If Rate Limits have been passed for User.
{
"success": False,
"message": "Rate limits have been passed for the user.",
}
  • If NSFW words are detected
{
"success": False,
"message": "NSFW words detected. Please try again with different lyrics.",
}
  • If Artist name is detected
{
"success": False,
"message": "Artist name detected. Please try again with different lyrics.",
}
⌘I