All Models
Lyria 3 Pro
Lyria 3 Pro generates music from a text prompt, with optional image conditioning.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Lyria 3 Pro
Lyria 3 Pro is Google DeepMind’s music model. You give it a text prompt and it composes a track. There is no lyrics field, no duration slider, and no voice id. The model decides how the piece unfolds.
You can also pass a still so the picture conditions the mood of the track, plus a negative prompt to keep out a genre or an instrument, and a seed so a take you like can be reproduced while you adjust the description.
The still is conditioning, not a music video. This model returns audio.
What it's good for
Score and song from a description, especially when a key-art still or a frame grab should set the mood. Useful against a mood board or a locked cut, because seed plus negative prompt lets you revise instead of rolling a new random piece each time.
Model ID
google/lyria-3-pro
Output Type
Audio
Pricing
$0.08
Provider
Hosting
Protoface
Lyria 3 Pro
Lyria 3 Pro is Google DeepMind’s music model. You give it a text prompt and it composes a track. There is no lyrics field, no duration slider, and no voice id. The model decides how the piece unfolds.
You can also pass a still so the picture conditions the mood of the track, plus a negative prompt to keep out a genre or an instrument, and a seed so a take you like can be reproduced while you adjust the description.
The still is conditioning, not a music video. This model returns audio.
What it's good for
Score and song from a description, especially when a key-art still or a frame grab should set the mood. Useful against a mood board or a locked cut, because seed plus negative prompt lets you revise instead of rolling a new random piece each time.