stability-ai/stable-audio-2.5

Stable Audio 2.5 generates music and sound effects from a text description.

$0.20 / request
GPU: A100

Model Inputs

string

The prompt to generate audio from

integer

The duration of the audio clip to generate

integer

The number of steps to denoise the audio for

number

How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).

integer

Seed

Result

Idle
Waiting for your input...

Pricing

stability-ai/

stable-audio-2.5

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
$0.20 / request
or
5 requests / $1

For example, generating 100 requests costs about $20.00.

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

ProviderPrice ($)Saving (%)
Synexa$0.20-
fal$0.20same price

Readme

Stable Audio 2.5 covers both ends of audio generation: musical passages and discrete sound effects, up to 190 seconds long.

It needs very few steps - 4 to 8 - which makes it quick. Raise guidance_scale to hold closer to the prompt wording, lower it for more musical freedom.