SAM Audio
SAM Audio (Segment Anything in Audio)
Segment Anything — for sound
Latest: SAM Audio v1 (Dec 16, 2025) — checkpoints small/base/large plus -tv variants; no 1.1 or newer release as of Sep 2026 (no tagged GitHub releases; arXiv paper still v1)
Family of open-weight foundation models that isolate any sound from a complex mixture using text prompts, visual prompts (click the object making the sound in a video), or time-span prompts. A flow-matching diffusion transformer built on Meta's Perception Encoder Audiovisual (PE-AV), it achieves state-of-the-art results across speech, music, instrument, and general sound separation.
Why it matters
Brings the Segment Anything idea to sound: describe a source, click the object making it in a video, or mark a time span, and it isolates that sound from a mixture with state-of-the-art results across speech, music and general audio. Open weights and a browser playground make source separation usable by editors, not only researchers.
Facts
- Announced Dec 16, 2025 (about.fb.com); arXiv:2512.18099 submitted Dec 19, 2025 (14 authors, first author Bowen Shi).
- Model sizes span ~500M to 3B parameters yet run faster than real time (RTF ≈ 0.7).
- Six main checkpoints on Hugging Face (facebook/sam-audio-{small,base,large} plus -tv variants tuned for target correctness/visual prompting) — gated access, ~19K downloads/month for sam-audio-large alone.
- GitHub repo has ~3.6K stars.
- Time-span prompting was billed by Meta as an industry first.
Try it yourself
Try it in the Segment Anything Playground ↗ Model on Hugging Face (large) ↗ Code on GitHub ↗
Lineage
Sources
arXiv ↗GitHub · sam-audio ↗Hugging Face ↗Live demo ↗Meta AI blog ↗Meta AI research ↗Meta Newsroom ↗