Skip to main content
🎵

Stable Audio

by Stability AI

Stable Audio is Stability AI's generative AI tool for creating original music tracks and sound effects from text prompts. It generates high-quality stereo audio up to several minutes long and is designed for musicians, sound designers, and content creators seeking royalty-free audio.

Stable Audio features and capabilities, including which plan they need and how they compare in the CanIUse matrix.

Used in combinations

See who owns what in this stack

Directory alternatives

✨ Modalities

💬
Text Input
Yes, requires plus plan. Text prompts drive music and SFX generation.
🖼️
Image Upload / Vision
No. Audio product, not vision.
🎨
Image Generation
No. Distinct from Stable Diffusion image models.
🎙️
Voice Mode
No. Music/SFX generation, not a voice chat assistant.
🎥
Video Understanding
No. Not a video product.
🎬
Video Generation
No. Not a video generation product.
📁
File Upload (PDF, DOCX)
Partial. Audio-to-audio workflows accept reference audio.
💻
Code Execution
No. Not a code sandbox.
🔊
Audio Input
Yes, requires plus plan. Audio-to-audio transformation is a listed capability.
🖌️
Canvas / Artifact Editor
No. Audio timeline in DAW, not a text canvas.
🖥️
Screen Sharing / Computer Use
No. No computer-use product.

🧠 Memory & Context

🧠
Persistent Memory
No. Generations are jobs, not persistent chat memory.
📏
Large Context Window
No. Not an LLM chat product.
⚙️
Custom Instructions
Partial. Prompt and style controls per generation.
📜
Conversation History
Partial. Web app may show past generations. API is per-call.

🔌 Integrations

🌐
Web Search / Browsing
No. Not a search product.
🔌
Plugins / Extensions
Partial. DAW plugin integrates into production workflows.
🔧
API Access
Yes, requires plus plan. Stable Audio API for music/SFX generation.
⚡
Zapier Integration
Unknown. Zapier was not checked.
🤖
Custom GPTs / Bots
No. Not a bot platform.
👥
Real-time Collaboration
No. No multiplayer editing advertised.
🐦
Live Social Data Integration
No. No social firehose.
📚
Live Citation Mapping
No. Not a search product.

👨‍💻 Developer

🛠️
Function Calling
No. Not an LLM with tools.
⚡
Streaming Responses
Partial. Generation may stream audio output in the web app.
🎛️
Fine-Tuning
Partial. Community LoRA mentioned; not a first-party fine-tune SKU.
📐
Embeddings API
No. Not an embeddings product.
📋
Structured Output (JSON)
No. Outputs audio files, not JSON schemas.
🧩
Reasoning / Thinking Mode
No. Not a reasoning LLM.
🏠
Local Execution
Partial. Community ONNX CPU inference mentioned; hosted API is cloud.
🔓
Open Weights
Partial. Some open/community weights exist; flagship models are Stability-hosted.
🤖
Multi-Agent Orchestration
No. Not an agent platform.

📱 Platforms

🌐
Web App
Yes, requires plus plan. stableaudio.com web generator.
📱
iOS App
Unknown. Mobile app was not checked.
🤖
Android App
Unknown. Mobile app was not checked.
🖥️
Desktop App
Partial. DAW plugin runs inside desktop audio software.
🔵
Chrome Extension
No. No Chrome extension.

🔒 Privacy

🔒
GDPR Compliant
Unknown. Privacy policy was not re-read.
🚫
Opt Out of Data Training
Unknown. Training on uploads was not checked.
🏢
Enterprise Privacy Mode
Unknown. Enterprise terms were not read.

💼 Workspaces

📂
Projects / Folders
Partial. Web account may store generations.