Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Soniox / Soniox STT

STT Async Preview v1

Historical STT Async Preview v1 release; current compatibility IDs may route to newer model generations.

retiredClosed weightsTranscription
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
3 of 16 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedSoniox API
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
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not supportedSource for Streaming (opens in a new tab)

Async file transcription; polling a queued job is not streaming inference.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
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.

API model ID
stt-async-preview-v1
Access
Original release is retired. Historical redirect information does not prove access to original weights.
Regions
Historical deployment region not established.
Equivalent API aliases
stt-async-v3Source for Equivalent API aliases (opens in a new tab)

Retirement was accelerated to October 31, superseding the previously planned November 30 date.

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

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

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.

Soniox API

stt-async-preview-v1
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

The provider identifies its hosted models as Soniox intellectual property, grants limited service access and prohibits extraction/reverse engineering. Native release documentation and historical reports establish these model identities; no public weight license is inferred from SDK availability.

Classification evidence (opens in a new tab)

Lifecycle dates

Original model retired; compatibility ID redirected31 Oct 2025Source (opens in a new tab)

Sources reviewed