Generative audio APIs
Create music, instruments, and sound effects from text prompts, transform existing audio with audio-to-audio workflows, or replace part of a track with audio inpainting.
Stability AI Developer Platform provides APIs for adding generative audio, image, image editing, upscaling, control, and 3D asset creation to applications. It is intended for developers and teams building creative workflows with Stability AI models.
Stability AI Developer Platform is an API platform for building applications around generative media. Its services cover text-to-audio, audio-to-audio, and audio inpainting, alongside image generation, image editing, upscaling, reference-based control, and 3D asset generation from a single image.
The platform offers multiple models and services for different output and speed requirements. Image options include Stable Image Ultra, Stable Image Core, Stable Diffusion 3.5 variants, and SDXL 1.0. Audio generation is provided through Stable Audio models, while separate services handle image transformation and 3D generation.
Developers access the API through an account and API key. Usage is credit-based: one credit equals $0.01, and new accounts can get 25 free credits according to the pricing page. The platform also provides a playground, documentation, release notes, API status information, and support resources.
Create music, instruments, and sound effects from text prompts, transform existing audio with audio-to-audio workflows, or replace part of a track with audio inpainting.
Choose among Stable Image Ultra, Stable Image Core, Stable Diffusion 3.5 Large, Large Turbo, Medium, Flash, and SDXL 1.0 for image-generation workflows.
Erase objects, inpaint masked areas, outpaint beyond an image’s boundaries, remove backgrounds, recolor or replace searched objects, and replace backgrounds while adjusting lighting.
Use Fast, Conservative, or Creative Upscaler services to increase resolution, with different approaches to speed, fidelity, and prompt-guided reinterpretation.
Guide image generation with structure, sketches, style references, or style transfer to support more controlled and consistent visual output.
Generate 3D assets with Stable Fast 3D or use Stable Point Aware 3D for real-time edits and reconstruction from a single image.
Add prompt-based image or audio generation to design, media, or content applications without building generative models from scratch.
Build workflows for removing backgrounds, erasing unwanted objects, repairing masked regions, extending canvases, and upscaling low-resolution images.
Use sketches, structure inputs, and reference styles to create variations that follow an existing visual direction.
Turn a single 2D input image into a 3D asset, then use the resulting capability in applications that need rapid object creation or editing.
Create an account, sign in to the account page, and create an API key there. The platform’s getting-started documentation provides additional guidance.
Confirm that the key is valid, that the account has sufficient credits, and that the key was copied correctly. Stability AI also recommends creating a new key if necessary.
Usage is based on credits, with one credit equal to $0.01 on the pricing page. The page lists different credit prices for audio, image, editing, control, upscaling, and 3D services, and notes that pricing can change. New accounts can start with 25 free credits.
Yes, according to the FAQ, provided the output does not violate copyrights. Use remains subject to the Stability AI Terms of Service and other applicable policies.
The API allows 150 requests every 10 seconds. Requests beyond that limit receive a 429 response and are timed out for 60 seconds. Developers needing a higher limit are directed to contact Stability AI.
modelslab.com
ModelsLab is a developer platform that provides APIs for image, video, audio, 3D, and LLM generation through a unified service. It supports teams building generative media features without integrating each model provider separately.
apiin.one
API in One is a unified AI API gateway for website owners and developers who need image, video, music, speech, chat, and AI tool capabilities through one API key and shared credit balance.
apiframe.ai
Apiframe is a unified REST API for generating AI images, videos, and music. It helps developers and automation teams add media generation through one API, with asynchronous jobs, webhooks, SDKs, and CDN-hosted outputs.
runwayml.com
Runway Dev is an API platform for adding AI-generated video, images, and audio to products and production workflows. It provides access to Runway and other providers' models, along with model routing, workflows, recipes, and team controls.
www.imejis.io
Imejis.io is an image generation platform with a remote MCP server and REST API for creating, editing, and rendering structured designs. It helps AI-agent users, developers, and automation workflows turn templates or structured data into PNG, JPEG, WebP, and single-page PDF outputs.
avaturn.me
Create realistic 3D avatars from selfies and embed them in apps, games, metaverse experiences, and campaigns.