Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Speechmatics / Speechmatics bilingual

Spanish–English Bilingual

Named language-specialized bilingual model for recognizing Spanish and English in one conversation.

availableClosed weightsTranscription
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
6 of 17 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedSpeechmatics 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
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Context caching
Not collected
Required request fields
language=es; model=enhanced or standard; domain=bilingual-enSource for Required request fields (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.

API model ID
Not collected

Choose enhanced or standard; the bilingual identity is carried by language/domain fields, not a single dedicated model ID.

Access
Named language pack on the standard API. The model and language/domain fields must be configured together; this is not a standalone checkpoint ID.
Regions
Europe example; see provider authentication for other region hosts.
API endpoint URL
https://eu1.asr.api.speechmatics.com/v2/jobs/Source for API endpoint URL (opens in a new tab)
Maximum audio file
Less than 1 GB for direct upload; larger files can be fetched by URLSource for Maximum audio file (opens in a new tab)
Request quotas
Guidance: 10 submissions/s and 50 status reads/s; backstop 20,000 concurrent jobsSource for Request quotas (opens in a new tab)
Request mode
Asynchronous Batch job; retrieve results or use completion notificationsSource for Request mode (opens in a new tab)
Required request fields
language=es; model=enhanced or standard; domain=bilingual-enSource for Required request fields (opens in a new tab)

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

Data & enterprise terms

Provider documentation says Realtime processing is in memory without storing audio or transcripts; Batch jobs retain audio, transcripts and configuration for seven days, with earlier deletion available. Current terms require opt-in before using customer data for training. Discounts based on training-data use require explicit opt-in; TTS preview documentation describes a different retention policy.

Read the service policy (opens in a new tab)
API model ID
Not collected

Choose enhanced or standard; the bilingual identity is carried by language/domain fields, not a single dedicated model ID.

Access
Named language pack on the standard API. The model and language/domain fields must be configured together; this is not a standalone checkpoint ID.
Regions
Europe example; see provider authentication for other region hosts.
API endpoint URL
wss://eu.rt.speechmatics.com/v2Source for API endpoint URL (opens in a new tab)
Session duration
48 hours maximum; also closes after one hour without audio or three minutes without audio/pingsSource for Session duration (opens in a new tab)
Request quotas
Free: two concurrent sessions; Pro: 50; Enterprise: agreed limitsSource for Request quotas (opens in a new tab)
Required request fields
language=es; model=enhanced or standard; domain=bilingual-enSource for Required request fields (opens in a new tab)

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

Data & enterprise terms

Provider documentation says Realtime processing is in memory without storing audio or transcripts; Batch jobs retain audio, transcripts and configuration for seven days, with earlier deletion available. Current terms require opt-in before using customer data for training. Discounts based on training-data use require explicit opt-in; TTS preview documentation describes a different retention policy.

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.

Speechmatics API

Not verified

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

How it works
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Minimum reusable input
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Lifetime & refresh
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

How to enable it
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Usage fields
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Billing rules
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Limits & data boundaries
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

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

Speechmatics API

Not verified

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

How it works
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Minimum reusable input
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Lifetime & refresh
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

How to enable it
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Usage fields
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Billing rules
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model prompt caching.

Limits & data boundaries
Not collected

No provider prompt-cache contract collected. Custom vocabulary, cached generated audio files and local Docker image caching do not establish model 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

Speechmatics identifies these as its own models or software, retains the software intellectual property and prohibits alteration/reverse engineering. Licensed containers and a native library do not grant an open model-weight license; SDK source availability is separate.

Classification evidence (opens in a new tab)

Sources reviewed