cinemasetfree
← Back to all generators
google/lyria-3.5
OfficialView on Replicate →
Generate full-length songs with vocals and lyrics from text prompts or images with Lyria 3.5, Google's most capable music generation model
Capabilities
Seed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt* | string | Text prompt for the song. Can include lyrics, section tags like [Verse] and [Chorus], and timestamps like [0:00 - 0:30] | — | — |
images | array | Input images to inspire the song (up to 10) | | — |
output_format | string | Format of the output audio | "mp3" | mp3wav |
seed | integer | Random seed. Omit for random generations | — | — |
promptrequiredstringText prompt for the song. Can include lyrics, section tags like [Verse] and [Chorus], and timestamps like [0:00 - 0:30]
imagesarrayInput images to inspire the song (up to 10)
Default:
output_formatstringFormat of the output audio
Default:
"mp3"mp3wav
seedintegerRandom seed. Omit for random generations
Version:
0d4134b1a7dfUpdated: 11/7/202638 runs