Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Resemble AI / Resemble detection and provenance

DETECT-2B

Audio-authenticity detection using an ensemble of representation models and sequence classifiers.

Deepfake detection
restrictedClosed weightsDeepfake detection
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
5 of 16 specification fields collected
Media analyzedAudioSee specification notes below
Analysis outputClassification scoresSee specification notes below
Input billingNot collectedResemble AI
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
AudioSource for Input modalities (opens in a new tab)
Output modalities
Classification scoresSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)

Model page advertises batches. Current service limits are not assumed to be historical version limits.

Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Ensemble with self-supervised audio representations, adaptation modules and Mamba state-space sequence modelingSource for Architecture (opens in a new tab)
Languages
More than 30 languages, provider-reportedSource for Languages (opens in a new tab)
Context caching
Not collected

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Resemble AI

Provider source (opens in a new tab)
API model ID
Not collected

No public request selector pins this model version.

Access
Contact Resemble for this named model or a pinned enterprise deployment. Current shared API access does not establish version selection.
Regions
Region and data residency not established for this access path.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Terms distinguish voice Content from Detection Media. Detection Media is not used for model training without express written opt-in. Deletion/retention follow service policies and any applicable DPA; no unconditional zero-retention guarantee.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Resemble AI

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Provider documentation establishes the named native model or managed composition. Terms expressly reserve proprietary voice/detection technology and prohibit reverse engineering of models. Public-weight Chatterbox, original PerTh and Resemblyzer are excluded; enterprise on-premises delivery is not treated as a public weight release.

Classification evidence (opens in a new tab)

Sources reviewed