stability-ai/stable-audio-2.5
Generate music and sound effects from a text prompt. Optionally extend or inpaint an input audio clip for seamless conti...
Sound effect generation models create short audio clips from prompts or conditioning inputs. They are useful for game prototypes, video production, UI sounds, ambience, Foley concepts, and rapid sound design exploration.
Compare models by clip length, prompt control, sample rate, noise level, and whether the output loops or layers cleanly. For games and video, timing and editability often matter as much as raw audio quality.
Found 21 models (showing 1-20)
Generate music and sound effects from a text prompt. Optionally extend or inpaint an input audio clip for seamless conti...
Generate audio clips from a text prompt. Input a descriptive prompt and a target duration to synthesize music, ambience,...
Generate synchronized environmental sounds and sound effects from a video input. Produce context-aware audio aligned to...
Generate audio from a text prompt. Produce sound effects, human speech, and music, with controls for clip duration and t...
Generate audio from a text prompt, including sound effects, ambience, and musical textures. Accepts a prompt (and option...
Generate synced sound effects for a silent video and return the video with a new soundtrack. Take a video input (max 10s...
Generate synchronized audio for a video from a video input and optional text prompt, with an option to produce piano acc...
Add synchronized environmental sound and foley to videos based on visual content. Accepts a video and an optional text p...
Generate sound effects from a text prompt. Takes a text description and optional duration (1–10 seconds) and outputs an...
Generates music from text prompts using a non-autoregressive transformer architecture. Offers multiple model sizes (300M...
Generate synchronized Foley sound effects from a video input and optional text prompt. Condition on visual content and s...
Generate short audio samples and sound effects from text prompts. Provide a prompt with optional controls for duration (...
Generate audio from a text prompt. Produce 44.1 kHz sound effects and ambiences from natural language with user-set dura...
Generate sound effects and general non-music audio from a text prompt. Accepts a textual description and returns an audi...
Generate music and audio textures from noise using an unconditional audio diffusion model. Configure clip length (second...
Generates algorithmic 8-bit synthesizer music from automatically created mathematical expressions. Uses grammar-constrai...
Generates speech and audio from text prompts using a transformer-based model. Supports multilingual speech generation wi...
Generate speech, music, background noise, and simple sound effects from a text prompt. Output an audio file, with an opt...
Generate contextual audio for videos from a video input with optional text guidance, returning a video with a synchroniz...
Generate synchronized sound effects for silent videos and return the video with a new soundtrack. Takes a video input (u...
Before using generated sound effects in production, check licensing, loudness, clipping, looping behavior, and how the sound sits in a full mix. Generate multiple variations so editors or designers can choose the version that fits the scene.