by Stability AI
Stability AI's family of text-to-audio models for music and SFX, with open-weight Small and Medium variants and an API-only Large.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Stable Audio 3.0 is a family of audio generation models from Stability AI, trained on fully licensed data. It comprises four models: Small SFX (on-device sound effects), Small (full music composition on-device, up to two minutes), Medium (better structure and melodic coherence, up to 6:20), and Large (highest musicality, aimed at music platforms needing low-latency, high-volume generation). It uses a new semantic-acoustic autoencoder and a variable-length generation method with per-second granularity.\n\nThe models support audio inpainting (single-segment editing, multi-segment editing and causal continuation to extend audio) and LoRA fine-tuning on a user's own audio library. Stability says it is publishing LoRA training documentation alongside the Small and Medium weights, and offers fine-tuning support under its Enterprise license.\n\nSmall SFX, Small and Medium are open-weight and downloadable from Hugging Face under the Stability AI Community License. Organizations with more than $1M in annual revenue need the Enterprise license. Large is available through the Stability AI API and self-hosting for enterprise deployments. Stability says ComfyUI and other partner platforms will support it.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Family of audio generation models with open-weight small and medium (1.4B, up to 6:20) variants, a small SFX version, and an API-only large model. Supports LoRA training and audio inpainting.
Model family generating up to 6-minute songs and sound effects; small and medium models are open weights while the largest 2.7B model is closed.
Closest neighbours by meaning, not just by category.
Model
Open-source diffusion-based music generation foundation model with lyric-aligned vocals and editing controls.
Model · ACE Studio
Open-source local music generation model with a 4B-parameter DiT decoder, extending ACE-Step 1.5 with higher audio quality.
Research · MiniMax
Open-weight multimodal model from MiniMax whose video pipeline can be run audio-only to generate music and sound effects.
Model · Google
Google DeepMind's music generation model producing vocal tracks up to 3 minutes from text or image prompts.
Model
Open-source local AI model for generating music loops, with reference-loop stacking and MIDI conversion.
Model · MiniMax
Open-weights text-to-music model from MiniMax that generates songs with vocals and lyrics across genres and languages.
