Audio-to-Audio (Reference-based Music Generation)

POST

/sd/v2beta/audio/stable-audio-2/audio-to-audio

Stable Audio can transform existing audio samples into new high-quality works, up to three minutes long, in 44.1kHz stereo, using text prompts. Explore sample transformation techniques in our "Audio-to-Audio Guide" to maximize creative control. Read more about model capabilities here.

Pricing: 0.02PTC/credits

stable-audio-2 typically consumes 20-23 credits, which is 0.4-0.46ptc
stable-audio-2.5 consumes a fixed 20 credits, which is 0.4ptc

Request

Query Params

Header Params

Body Params application/json

Example

{
    "prompt": "string",
    "audio": "string",
    "output_format": "string",
    "seed": 0,
    "steps": 0,
    "duration": 0,
    "cfg_scale": 0,
    "model": "string"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/sd/v2beta/audio/stable-audio-2/audio-to-audio?response_format=url' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "string",
    "audio": "string",
    "output_format": "string",
    "seed": 0,
    "steps": 0,
    "duration": 0,
    "cfg_scale": 0,
    "model": "string"
}'

Responses

🟢200Success

application/json

Body

Example

{}

Modified at 2025-09-29 02:31:48

Text-to-Audio (Text-generated Music)

Inpaint (Music Editing/Modification)