google/lyria-2

Lyria 2 generates 30 seconds of 48kHz music from a descriptive text prompt.

$0.10 / request
GPU: A100

Model Inputs

string

The text prompt describing the music you want to generate

string

A description of what to exclude from the generated audio

integer

A seed for deterministic generation. If provided, the model will attempt to produce the same audio given the same prompt and other parameters.

Result

Idle
Waiting for your input...

Pricing

google/

lyria-2

Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.

Output
$0.10 / request
or
10 requests / $1

For example, generating 100 requests costs about $10.00.

Check out our docs for more information about how per-request pricing works on Synexa.

ProviderPrice ($)Saving (%)
Synexa$0.10-
fal$0.10same price

Readme

Lyria 2 is Google's music generation model. It returns 30 seconds of 48kHz WAV audio.

Prompts work best when descriptive and specific. Cover genre and style, mood, instrumentation, tempo and rhythm, and any effects or soundscape; add production terms like "clean mix" or "vintage recording" to steer the sound. Use negative_prompt to exclude unwanted elements and seed for reproducibility.

Safety filters block inappropriate content.