MusicGen

Generate music based on textual prompts and optional conditioning melodies.

POST /voice/music_gen

Generate music from text prompt

cURL

curl --request POST \
  --url https://modelslab.com/api/v6/voice/music_gen \
  --header 'Content-Type: application/json' \
  --data '
{
  "key": "<string>",
  "prompt": "<string>",
  "init_audio": "<string>",
  "duration": 30,
  "output_format": "wav",
  "bitrate": "320k",
  "base64": false,
  "temp": false,
  "webhook": "<string>",
  "track_id": 123
}
'

200

{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "future_links": [
    "<string>"
  ],
  "links": [
    "<string>"
  ],
  "meta": {},
  "eta": 123,
  "message": "<string>",
  "tip": "<string>",
  "fetch_result": "<string>",
  "audio_time": 123
}

Request

Make a POST request to below endpoint and pass the required parameters as a request body.

curl

--request POST 'https://modelslab.com/api/v6/voice/music_gen' 

Body

Without init_audio:

json

{
    "key":"your_api_key",
    "prompt":"marimba, percussion, bass, tropical house, melodic riff, G# minor, 96 bpm",
    "duration": 30,
    "output_format": "wav",
    "bitrate": "320k",
    "base64":false,
    "temp": false,
    "webhook": null,
    "track_id": null
}

With init_audio:

json

{
    "key":"your_api_key",
    "prompt":"marimba, percussion, bass, tropical house, melodic riff, G# minor, 96 bpm",
    "init_audio":"https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/IxizU51vL2IwiEjy6XtvbDECa9f16E-metaU2hhcGUgb2YgeW91IFJpbmd0b25lIO+9nO+9nCBJbnN0cnVtZW50YWwgQkdNIO+9nO+9nCBMSUdIVCBHT0pPLndhdg==-.wav",
    "duration": 30,
    "output_format": "wav",
    "bitrate": "320k",
    "base64":false,
    "temp": false,
    "webhook": null,
    "track_id": null
}

Body

application/json

key · string · required

Your API Key for request authorization

prompt · string · required

Input text for music generation

init_audio · string<uri>

Conditioning melody URL for music generation (up to 30 seconds)

duration · integer · default: 30

Duration of the generated music in seconds. Any arbitrary value between 30 and 480. Default: 30.

Required range: 30 <= x <= 480

output_format · enum<string> · default: wav

Output format of the generated audio. Options: wav, mp3, flac. Default: wav.

Available options: wav, mp3, flac

bitrate · enum<string> · default: 320k

Bitrate of the generated audio file. Options: 128k, 192k, 320k. Default: 320k.

Available options: 128k, 192k, 320k

base64 · boolean · default: false

Whether input sound clip is in base64 format

temp · boolean · default: false

Use temporary links for regions blocking storage access

webhook · string<uri>

URL to receive POST callback upon completion

track_id · integer

Unique ID for identifying webhook responses

Response

200

application/json

Music generation response

status · enum<string>

Status of the voice generation

Available options: success, processing, error

generationTime · number

Time taken to generate the audio in seconds

id · integer

Unique identifier for the voice generation

output · string<uri>[]

Array of generated audio URLs

proxy_links · string<uri>[]

Array of proxy audio URLs

future_links · string<uri>[]

Array of future audio URLs for queued requests

links · string<uri>[]

Array of audio URLs (voice cover response)

meta · object

Metadata about the audio generation including all parameters used

eta · integer

Estimated time for completion in seconds (processing status)

message · string

Status message or additional information

tip · string

Additional information or tips for the user

fetch_result · string<uri>

URL to fetch the result when processing

audio_time · number

Duration of the generated audio in seconds