Enterprise AI Resource Hub - 302.AI | Pay-as-you-go, Comprehensive AI model API Access, Instant Online App Usage

stable-audio-2.0

Text-to-audio technology and models launched by Stability AI

2025-09-29

Audio-Video Processing

Pricing:

$0.02/credits

starting from

Bulk order? Contact your manager for exclusive deals

API Overview

Stable Audio can generate high-quality music and sound effects lasting up to three minutes based on text descriptions, with a sampling rate of 44.1 kHz stereo. Refer to our prompt guide to learn how to write effective prompts for optimal generation results. Stable Audio 2.5: Fast, High-Quality, Long-Form Music and Audio Generation Our state-of-the-art audio generation model is capable of producing works up to 3 minutes long in 44.1 kHz stereo. Stable Audio 2.5 supports text-to-audio, audio-to-audio, and audio-patching workflows—allowing creators to upload sounds and transform them into new instruments, styles, or genres using natural language prompts. It’s perfect for music production, cinematic sound design, and mixing. Stable Audio 2.0: High-Quality Audio Generation Built specifically for text-to-audio and audio-to-audio tasks, Stable Audio 2.0 also generates up to 3 minutes of 44.1 kHz stereo audio. Ideal for creative ideation, music demos, and atmospheric soundscapes, it’s optimized for professional creators seeking detailed, longer outputs from simple prompts.

Stable Audio 2 typically consumes 20–23 credits, equivalent to $0.4–$0.46 USD.

Stable Audio 2.5 is set to consume a fixed 20 credits, or $0.4 USD.

API Console

API Reference (2)

API Description	API Endpoint	Request Method	Stability	Parameter Description
Text-to-Audio (Text-generated Music)	https://api.302.ai/sd/v2beta/audio/stable-audio-2/text-to-audio	POST	Stable	View Details
Document Details 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 Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Query Parameters response_formatstring Optional Example Value:`URL` Request Body multipart/form-data promptstring Required Descriptive prompt required to generate audio, up to 10,000 characters. Example Value:`A cinematic orchestral score featuring violins and piano` durationnumber Optional Audio duration (seconds), range: 1-190, default: 190 Example Value:`The number of items per page.` seednumber Optional Random seed, range 0-4294967294; 0 means a random seed is used, default is 0. Example Value:`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.` stepsinteger Optional Sampling steps. For stable-audio-2: 30…100, for stable-audio-2.5: 4…8. Default is 50 or 8. Example Value:`50` cfg_scalenumber Optional Hint to follow intensity, range 1-25; default is 7 for stable-audio-2, and 1 for stable-audio-2.5 Example Value:`7` modelenum<string> Optional Generation model, optional: stable-audio-2, stable-audio-2.5; default is stable-audio-2 Enum Value: `stable-audio-2stable-audio-2.5` Example Value:`stable-audio-2.5` output_formatstring Optional Output format, optional values are mp3 or wav. Default is mp3. Example Value:`mp3`
Audio-to-Audio (Reference-based Music Generation)	https://api.302.ai/sd/v2beta/audio/stable-audio-2/audio-to-audio	POST	Stable	View Details
Document Details 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 Parameters Header Parameters Authorizationstring Optional Example Value:`Bearer {{YOUR_API_KEY}}` Query Parameters response_formatstring Optional Example Value:`url` Request Body application/json promptstring Required Required String <= 10,000 characters Describe the desired characteristics of the output audio. A strong, descriptive prompt that clearly defines instruments, mood, style, and genre will yield better results. You can make the prompt as simple or as complex as you like. Simple prompts tend to produce clean audio, while complex prompts can add texture and depth to the output. output_formatstring Optional string Default: mp3 Enum: mp3 wav Specifies the content-type of the generated audio. seednumber Optional Number [0 … 4294967294] Default: 0 A specific value used to guide the generation of “randomness.” (Omit this parameter or pass 0 to use a random seed.) stepsinteger Optional Integer Controls the number of sampling steps. For stable-audio-2: accepts steps between 30 and 100 (default is 50). For stable-audio-2.5: accepts steps between 4 and 8 (default is 8). durationnumber Optional Number [1 … 190] Default: 190 Controls the duration of the generated audio (in seconds). cfg_scalenumber Optional Number [1 … 25] The strictness with which the diffusion process follows the prompt text (the higher the value, the closer the audio matches the prompt). If not specified, defaults to 7 for stable-audio-2.1 and stable-audio-2.5. modelstring Optional string Default: stable-audio-2 Enum: stable-audio-2 stable-audio-2.5 The model used for generation. stable-audio-2.5 requires 20 credits per use stable-audio-2 requires 20 credits per use audiostring Required

API Pricing

$￥円 ₽

Model	Description	302.AI Price

Text-to-Audio (Text-generated Music)	-	$0.02/credits
Audio-to-Audio (Reference-based Music Generation)	-	$0.02/credits

stable-audio-2.0

API Overview

API Console

API Reference (2)

Header Parameters

Query Parameters

Request Body multipart/form-data

Header Parameters

Query Parameters

Request Body application/json

API Pricing

Text-to-Audio (Text-generated Music)

$0.02/credits

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

$0.02/credits

Recommended

Quick Access

Support

Legal Statement