stabilityai / stable-audio-3-medium

## Overview Stable Audio 3 Medium is an audio generation model from Stability AI. It uses latent diffusion over a compressed audio representation from a semantic-acoustic autoencoder. ([huggingface.co](https://huggingface.co/stabilityai/stable-audio-3-medium?utm_source=openai)) You write a text description and it produces a stereo music clip in a chosen format like MP3 or WAV. This is useful when you need custom music beds, loops, or draft tracks without clearing a sample library first. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) ## What you can build - Background music for videos, trailers, and reels - Game music drafts for menus, levels, and ambient zones - Podcast intro and outro music sketches - Mood boards for composers and audio directors - Variations on a musical idea by changing the prompt and seed ## Inputs - A required text description of the music you want (English works best). Include style, instruments, mood, and BPM when you can. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - An optional text description of what to avoid in the result (for example, “no vocals” or “avoid harsh distortion”). ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - The target length in seconds. The Medium model supports up to 380 seconds (about 6 minutes 20 seconds). ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - The number of denoising steps to use during sampling. More steps can change detail, but the post-trained checkpoint is designed to look good at low step counts. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - A guidance strength value that controls how tightly the output follows your prompt. (This control matters most on base, non-distilled checkpoints.) ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - An optional seed number for repeatable results. Omit it for a random result each run. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - An optional toggle to expand your prompt with an LLM, which can help when your prompt is short. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - An optional toggle to enable an NSFW safety checker. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - Your preferred audio container format for the output (MP3 is the default, and WAV/FLAC are available for lossless exports). ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - For compressed formats, an output bitrate string (for example, values like 192k or 320k). ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - An optional “inline return” mode that can return audio as a data URI instead of a hosted download. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) ## Outputs The model returns a generated audio file plus metadata. - An audio file object that includes a downloadable URL and file metadata such as MIME type, filename, and size. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - The seed that was used for the generation, so you can reproduce or iterate. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - The prompt text that was actually used for the generation. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) ## Recommended settings - Use 8 denoising steps for the post-trained Medium checkpoint. It is tuned to look good at that default. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - Keep guidance at 1.0 unless you are using a base (non-distilled) checkpoint. Guidance has limited effect on distilled checkpoints. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - Turn on prompt expansion when your prompt is short or vague. Leave it off when your prompt is already detailed. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - Export MP3 for quick review. Export WAV or FLAC when you plan to edit or master the result. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) ## Limitations - Maximum generation length for the Medium model is 380 seconds. Requests longer than that may fail or be truncated. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - The model is aimed at music generation. For pure sound effects, Stable Audio 3 Small SFX may be a better fit. ([github.com](https://github.com/Stability-AI/stable-audio-3/raw/refs/heads/main/docs/guides/prompting.md)) - Don’t expect clean, intelligible vocals. It can produce vocal-like textures, but words typically won’t be understandable. ([github.com](https://github.com/Stability-AI/stable-audio-3/raw/refs/heads/main/docs/guides/prompting.md)) - Vague or conflicting prompts often produce generic results. Add genre, instrumentation, and tempo to improve control. ([github.com](https://github.com/Stability-AI/stable-audio-3/raw/refs/heads/main/docs/guides/prompting.md)) - If you export to lossy formats (like MP3), compression artifacts can appear in cymbals and dense mixes. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) ## Safety & compliance - You can enable an NSFW safety checker. Turn it on if you accept public or user-generated prompts. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api)) - Stability AI states Stable Audio 3.0 models are trained on fully licensed data, and the open weights for Small and Medium are provided under a Stability AI Community License. ([stability.ai](https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models?utm_source=openai)) - Under Stability AI’s licensing terms, commercial use depends on your organization’s revenue tier. Review the Stability AI license terms before shipping a product. ([stability.ai](https://stability.ai/license?utm_source=openai))