Turn your words into expressive, AI-generated music and bring your stories, emotions, or ideas to life through sound.
Output: $0.15 / use or 6 uses / $1
Input
Output
text_to_music_output.mp3
Audio
{
"task_id": "db2x1fp43o3n10nuwb",
"user_id": 1,
"version": "280fc4f9ee507577f880a167f639c02622421d8fecf492454320311217b688f1",
"error": null,
"total_time": 6,
"predict_time": 6,
"logs": null,
"output": [
"https://vmodel.ai/data/model/vmodel/text-to-music/text_to_music_output.mp3"
],
"status": "succeeded",
"create_at": 1751596221,
"completed_at": 1751596227,
"input": {
"seed": -1,
"tags": "emotional,melancholic,piano,pop,male vocal,ballad,urban sadness",
"lyrics": "[verse]\nI left your cup right where you placed it\nStill warm, like you never faced it\nThe end we both anticipated\nBut no one ever really says it\n\n[chorus]\nWe’re too good at acting like we’re fine\nEven goodbye sounds like a borrowed line\nYou said “don’t hold on too tight”\nI smiled and said, “I’ll try”\n\n[verse]\nYou packed your words with quiet grace\nI memorized your empty face\nTried not to beg, tried to give space\nBut silence fills this broken place\n\n[chorus]\nWe’re too good at acting like we’re fine\nEven goodbye sounds like a borrowed line\nYou said “don’t hold on too tight”\nI smiled and said, “I’ll try”\n\n[bridge]\nLove slowed down like falling rain\nThe slower it gets, the clearer the pain\nYou didn’t cry, you just turned away\nI didn’t stop you — I had nothing to say",
"duration": 60,
"scheduler": "euler",
"guidance_type": "apg",
"guidance_scale": 15,
"number_of_steps": 60,
"granularity_scale": 10,
"guidance_interval": 0.5,
"min_guidance_scale": 3,
"tag_guidance_scale": 0,
"lyric_guidance_scale": 0,
"guidance_interval_decay": 0
}
}
Generated in: 6 seconds
Download
Input
Output
text_to_music_output.mp3
Audio
{
"task_id": "db2x1fp43o3n10nuwb",
"user_id": 1,
"version": "280fc4f9ee507577f880a167f639c02622421d8fecf492454320311217b688f1",
"error": null,
"total_time": 6,
"predict_time": 6,
"logs": null,
"output": [
"https://vmodel.ai/data/model/vmodel/text-to-music/text_to_music_output.mp3"
],
"status": "succeeded",
"create_at": 1751596221,
"completed_at": 1751596227,
"input": {
"seed": -1,
"tags": "emotional,melancholic,piano,pop,male vocal,ballad,urban sadness",
"lyrics": "[verse]\nI left your cup right where you placed it\nStill warm, like you never faced it\nThe end we both anticipated\nBut no one ever really says it\n\n[chorus]\nWe’re too good at acting like we’re fine\nEven goodbye sounds like a borrowed line\nYou said “don’t hold on too tight”\nI smiled and said, “I’ll try”\n\n[verse]\nYou packed your words with quiet grace\nI memorized your empty face\nTried not to beg, tried to give space\nBut silence fills this broken place\n\n[chorus]\nWe’re too good at acting like we’re fine\nEven goodbye sounds like a borrowed line\nYou said “don’t hold on too tight”\nI smiled and said, “I’ll try”\n\n[bridge]\nLove slowed down like falling rain\nThe slower it gets, the clearer the pain\nYou didn’t cry, you just turned away\nI didn’t stop you — I had nothing to say",
"duration": 60,
"scheduler": "euler",
"guidance_type": "apg",
"guidance_scale": 15,
"number_of_steps": 60,
"granularity_scale": 10,
"guidance_interval": 0.5,
"min_guidance_scale": 3,
"tag_guidance_scale": 0,
"lyric_guidance_scale": 0,
"guidance_interval_decay": 0
}
}
Generated in: 6 seconds
Download
HTTP Request
Run vmodel/text-to-music:280fc4f9ee507577f880a167f639c02622421d8fecf492454320311217b688f1 using Vmodel's HTTP API.
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
tags
Type:string
Default value:-
Description:Text prompts to guide music generation, e.g., 'epic,cinematic'
lyrics
Type:string
Default value:
Description:Lyrics for the music. Use [verse], [chorus], and [bridge] to separate different parts of the lyrics. Use [instrumental] or [inst] to generate instrumental music
duration
Type:int
Default value:60
Description:Duration of the generated audio in seconds. -1 means a random duration between 30 and 240 seconds.
Range:
Min: 1
|
Max: 240
seed
Type:int
Default value:-1
Description:Random seed. Set to -1 to randomize.
number_of_steps
Type:int
Default value:60
Description:Number of inference steps.
Range:
Min: 10
|
Max: 200
scheduler
Type:enum
Default value:euler
Description:Scheduler type.
Choices:euler, heun
guidance_type
Type:enum
Default value:apg
Description:Guidance type for CFG.
Choices:apg, cfg, cfg_star
granularity_scale
Type:int
Default value:10
Description:Omega scale for APG guidance, or similar for other CFG types.
Range:
Min: -100
|
Max: 100
guidance_interval
Type:float
Default value:0.5
Description:Guidance interval.
Range:
Min: 0
|
Max: 1
guidance_interval_decay
Type:float
Default value:0
Description:Guidance interval decay.
Range:
Min: 0
|
Max: 1
guidance_scale
Type:int
Default value:15
Description:Overall guidance scale.
Range:
Min: 0
|
Max: 30
min_guidance_scale
Type:int
Default value:3
Description:Minimum guidance scale.
Range:
Min: 0
|
Max: 100
tag_guidance_scale
Type:int
Default value:0
Description:Guidance scale for tags (text prompt).
Range:
Min: 0
|
Max: 10
lyric_guidance_scale
Type:int
Default value:0
Description:Guidance scale for lyrics.
Range:
Min: 0
|
Max: 10
Pricing
Model pricing for vmodel/text-to-music. Looking for volume pricing? Get in touch.