Text-to-Audio (Text-generated Music)

POST

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

Stable Audio can generate up to three minutes of high-quality music and sound effects based on text descriptions, with a 44.1kHz stereo sampling rate. Refer to our prompt guide to learn how to write effective prompts for the best generation results.

Stable Audio 2.5: Fast, High-Quality, Long-Form Music and Audio Generation
Our most advanced audio generation model, capable of producing up to 3 minutes of 44.1 kHz stereo audio. Stable Audio 2.5 supports text-to-audio, audio-to-audio, and audio inpainting workflows—creators can upload sounds and transform them into new instruments, styles, or genres using natural language prompts. Ideal for music production, cinematic sound design, and remixing.

Stable Audio 2.0: High-Quality Audio Generation
Designed for text-to-audio and audio-to-audio tasks, it also generates up to 3 minutes of 44.1 kHz stereo audio. Stable Audio 2.0 is perfect for creative ideation, music demos, and ambient soundscapes. It is optimized for professional creators seeking detailed and longer outputs from simple prompts.

Pricing: 0.02PTC/credits

stable-audio-2 typically consumes 20-23 credits, i.e., 0.4-0.46ptc
stable-audio-2.5 consumes a fixed 20 credits, i.e., 0.4ptc

Request

Query Params

Header Params

Body Params multipart/form-data

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/text-to-audio?response_format=URL' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--form 'prompt="A cinematic orchestral score featuring violins and piano";type=text/plain' \
--form 'duration="The number of items per page.";type=text/plain' \
--form 'seed="I'\''m sorry, but there is no parameter or description provided for translation. Please provide the request parameter or response description you would like translated.";type=text/plain' \
--form 'steps="50";type=text/plain' \
--form 'cfg_scale="7";type=text/plain' \
--form 'model="stable-audio-2.5";type=text/plain' \
--form 'output_format="mp3";type=text/plain'

Responses

🟢200Success

application/json

Body

Example

{}

Modified at 2025-09-29 02:31:37

Retrieve task result

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