Generate music based on text description and style preferences. Supports vocal songs and instrumental music.
Important: At least one of description or styles must be provided.
When type is ONLY_MUSIC, the result will not include lyrics or cover image.
Authenticate using Bearer token. Get your API Key from the WeryAI Console.
Example: Authorization: Bearer sk-xxxxxxxxxxxxxxxx
At least one of description or styles must be provided.
Music type
VOCAL_SONG, ONLY_MUSIC "VOCAL_SONG"
Describe the song style, mood, instruments, etc. Used as the generation prompt. Required if styles is not provided.
"A cheerful pop song about summer vacation"
Lyrics content. If not provided, AI will auto-generate lyrics. Not applicable for ONLY_MUSIC type.
"Sunshine on my face, wind in my hair\nSummer days without a care"
Reference audio file URL for style guidance
"https://example.com/reference.mp3"
Name of the reference audio file
"reference_track"
Singer gender, recommended for VOCAL_SONG type
m, f "f"
Music style tags as key-value pairs. Keys must be valid style enum names (uppercase), values are the style descriptions used in generation.
Required if description is not provided.
Available style keys by category:
| Category | Available Keys |
|---|---|
| Genre | POP, ROCK, RAP, ELECTRONIC, RNB, JAZZ, FOLK, CLASSIC, WORLD |
| Emotion | HAPPY, RELAXED, WARM, ROMANTIC, TOUCHING, SAD, LONELY, DEPRESSED, TENSE, EXCITED, EPIC, MYSTERIOUS |
| Instrument | PIANO, GUITAR, BASS, DRUMS, STRINGS, WIND, SYNTHESIZER, ELECTRONIC_SOUND, FOLK_INSTRUMENT, MIXED_ORCHESTRATION |
You can combine multiple styles across categories.
{
"POP": "pop",
"HAPPY": "happy",
"PIANO": "piano"
}Callback URL where results will be sent when task completes
"https://your-server.com/webhook"
Caller ID (for business association)