Music

Generate full songs from a prompt.

POST /v1/music/generations

Generate music from text prompt

cURL

curl --request POST \
  --url https://api.infery.ai/v1/music/generations \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "operation": "generate",
  "images": [
    {
      "data": "<string>",
      "mime_type": "image/jpeg"
    }
  ],
  "response_format": "mp3",
  "custom_mode": true,
  "instrumental": true,
  "title": "<string>",
  "style": "<string>",
  "lyrics": "<string>",
  "negative_tags": "<string>",
  "vocal_gender": "m",
  "style_weight": 0.5,
  "weirdness_constraint": 0.5,
  "audio_weight": 0.5,
  "persona_id": "<string>",
  "persona_model": "style_persona",
  "audio_id": "<string>",
  "task_id": "<string>",
  "upload_url": "<string>",
  "continue_at": 123,
  "default_param_flag": true,
  "separation_type": "separate_vocal",
  "tags": "<string>",
  "sound_loop": true,
  "sound_tempo": 150,
  "sound_key": "<string>"
}
'

200

{
  "created": 1713204900,
  "data": [
    {
      "url": "https://storage.googleapis.com/.../music/...mp3?X-Goog-Signature=...",
      "b64_audio": "<string>",
      "content_type": "audio/mpeg",
      "duration_seconds": 30,
      "lyrics": "<string>"
    }
  ],
  "credits_used": 180
}

curl https://api.infery.ai/v1/music/generations \
  -H "Authorization: Bearer $INFERY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "suno-v4",
    "prompt": "Upbeat indie folk about a sunrise coastal drive",
    "duration_seconds": 60
  }'

Music generation is async — returns job_id, poll GET /v1/music/generations/:job_id for progress.

When complete you get a URL to the MP3 and separate stems if the model exposes them (Suno supports vocals + instrumentals).

Sample output

30-second clip generated with lyria-3-clip-preview (Google Lyria).

Parameters

• prompt — natural-language description
• style — optional style tag (lofi, synthwave, indie, etc.)
• lyrics — optional explicit lyrics
• vocal_gender — male, female, none
• duration_seconds — 30–180 (model-dependent)

Supported models

Suno (primary). Google Lyria when in beta. See Models → Music.

Authorizations

Authorization · string · header · required

API key in format: Bearer inf_***

Body

application/json

model · string · required

Model ID to use for music generation

prompt · string · required

Text prompt describing the music. For Lyria 3 Clip, always produces 30s. For Lyria 3 Pro, control duration via prompt or timestamps. For Suno, max 500 chars in non-custom mode, up to 5000 in custom mode.

operation · enum<string> · default: generate

Suno operation type. Default = generate. Other operations require additional fields (audio_id, upload_url, etc).

Available options: generate, extend, upload_cover, upload_extend, add_instrumental, add_vocals, sounds, vocal_removal, lyrics

images · object[]

Up to 10 base64-encoded images to inspire the music (Lyria 3 only)

Show child attributes

response_format · enum<string> · default: mp3

Output format. WAV only supported by Lyria 3 Pro and Suno.

Available options: mp3, wav

custom_mode · boolean

Suno: Enable custom mode (full control over style/title/lyrics)

instrumental · boolean

Suno: Generate instrumental track only (no vocals)

title · string

Suno: Track title (custom mode, max 100 chars)

style · string

Suno: Music genre/style (custom mode, max 1000 chars)

lyrics · string

Suno: Lyrics text (custom mode, when not instrumental)

negative_tags · string

Suno: Styles to exclude (e.g. "Heavy Metal, Upbeat Drums")

vocal_gender · enum<string>

Suno: Preferred vocal gender

Available options: m, f

style_weight · number

Suno: Style adherence weight (0.0-1.0)

Required range: 0 <= x <= 1

weirdness_constraint · number

Suno: Creativity/novelty constraint (0.0-1.0)

Required range: 0 <= x <= 1

audio_weight · number

Suno: Input audio influence weight (0.0-1.0)

Required range: 0 <= x <= 1

persona_id · string

Suno: Persona ID to apply (custom mode)

persona_model · enum<string>

Suno: Persona model type

Available options: style_persona, voice_persona

audio_id · string

Suno: Source audio ID (for extend, vocal_removal)

task_id · string

Suno: Task ID (vocal_removal — references original generation task)

upload_url · string

Suno: Audio file URL (for upload_cover, upload_extend, add_instrumental, add_vocals)

continue_at · number

Suno: Continue from this second mark (extend operations)

default_param_flag · boolean

Suno: Use default params (extend operations)

separation_type · enum<string>

Suno: Vocal removal type (2 stems vs up to 12 stems)

Available options: separate_vocal, split_stem

tags · string

Suno: Tags for add_instrumental operation

sound_loop · boolean

Suno sounds: Loop the generated sound

sound_tempo · integer

Suno sounds: BPM (1-300)

Required range: 1 <= x <= 300

sound_key · string

Suno sounds: Musical key

Response

200

application/json

Music generation result. Audio is uploaded to private storage and returned as a signed url (7-day expiry). If the storage upload fails, the response falls back to inline b64_audio.

created · integer

Unix timestamp (seconds) when the generation completed

Example:

1713204900

data · object[]

Show child attributes

credits_used · integer

Credits deducted from the workspace balance for this request

Example:

180