Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Apple / Apple Speech Components

Siri Expressive Voice Detokenizer

Streaming synthesis component downstream of AFM 3 Core Advanced. It transforms semantic audio tokens into residual-vector-quantized audio representations.

Audio processing
availableClosed weightsAudio processing
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
8 of 21 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesApple Siri Expressive Voices component
Output billingSee billing notesAccess and billing notes below

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 input tokens
Not collected
Maximum output
Not collected
Input modalities
Semantic audio tokensSource for Input modalities (opens in a new tab)
Output modalities
RVQ audio codesSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Streaming encoder, temporal decoder and reusable depth decoder with diffusion-transformer-style stage conditioningSource for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected
Provider-reported latency
About 10 ms per generation step, approximately 16× realtime on Apple AMXSource for Provider-reported latency (opens in a new tab)

Provider measurement of the detokenizer, not end-to-end LLM latency or a product SLA.

Memory and asset size
About 21 MB peak runtime memory; 329 MB on-device assetsSource for Memory and asset size (opens in a new tab)

Component figures, not total AFM 3 Core Advanced storage or RAM.

Evaluated audio duration
Continuous synthesis evaluated over 20–320 secondsSource for Evaluated audio duration (opens in a new tab)

Evaluation range, not a minimum or maximum API output duration.

Published price
Bundled production speech component; no standalone tariff verifiedSource for Published price (opens in a new tab)

Access & pricing

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

Apple Siri Expressive Voices component

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

Product or SDK model identity, not a verified public HTTP model selector.

Access
Deployed inside the speech pipeline. No independent public request selector or raw-component SDK access verified.
Regions
Supported Apple devices, OS versions, languages and regions only. A device-local model is not a guarantee of access in every market.

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

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

Apple Siri Expressive Voices component

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

Apple documents this proprietary product model. No matching unrestricted public checkpoint was verified in the reviewed Apple weight inventory. Closed-weight classification is inferred for this product identity; OS delivery and member-gated model assets do not imply an open-weight release.

Classification evidence (opens in a new tab)

Sources reviewed