AI Model Radar
中文 EN

SAM Audio

Meta
Model overview

SAM Audio

Meta's current public SAM Audio open-weight model for promptable audio extraction.

audio separationaudio editingevaluationlocal inference
CompareCompanyRankingsPublic signals
Representative version

SAM Audio

CompanyMeta
ReleaseNot disclosed
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiesaudio / text
Output modalitiesaudio
Tool use / function callingNot disclosed
Structured output / reasoningNot disclosed
Vision / audio / videoConfirmed: Audio
Open weights / LicenseWeights available / license pending verification
meta-sam-audio-current · License source pending verification
Vendor APINot disclosed
API source pending verification
OpenRouterNot separately listed on OpenRouter
PricingNo reliable public source
BenchmarkNo reliable public source
Public signals1 activity snapshot
Use casesaudio editing / research evaluation / local inference / audio separation
Claim evidenceRelease / model specs / weightsSAM Audio: A foundation model for promptable audio extraction | Meta AISAM Audio
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versionSAM Audio
meta-sam-audio-current
PricingNo reliable public source
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Public activity counters

Cumulative Hugging Face model-card downloads / likes / spaces

PlatformEntryDownloadsLikesSpacesTimeSource
huggingfacefacebook/sam-audio-large8,663420212026-07-15T20:11:41.551ZView source
Evidence gaps

Public display boundary

Parameter scale not disclosedRelease date not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed