Speechmatics

Speech-recognition and synthesis developer with general, multilingual, medical and voice-agent models, plus licensed local deployments.

Current native model families, six named bilingual variants, TTS, the 2026 on-device model and Ursa history reviewed. Language packs, model revisions, older generations and contract-specific access remain under review; this is not a complete historical census.

Closed-weight models

Browse by model typeCapabilities can overlap

Start with the job your model needs to do. Then narrow by capabilities, provider and price.

Select up to 3 models to compare

What does one question cost?

Compare every model with the same request.

Input tokensOutput tokens

Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.

17 models

Sort by

Model input and output limits, prices and estimated cost per question at the selected token counts.
Input tokensPublished limit*	Output tokensMaximum per response*	Input pricePer 1M tokens	Cost per question1,000 input + 500 outputEstimated · uncached
Less than 1 GB for direct Batch upload; larger files via fetch URLfile limit	Not collected	Usage pricing $0.75 / audio hourBatch transcription · Speechmatics API$0.80 / audio hourRealtime transcription · Speechmatics APIRates & conditions ↗	Different billing unitPrice details ↗
Less than 1 GB for direct Batch upload; larger files via fetch URLfile limit	Not collected	Usage pricing $0.45 / audio hourBatch transcription · Speechmatics API$0.45 / audio hourRealtime transcription · Speechmatics APIRates & conditions ↗	Different billing unitPrice details ↗
Less than 1 GB for direct Batch upload; larger files via fetch URLfile limit	Not collected	Usage pricing $0.24 / audio hourBatch transcription · Speechmatics APIRates & conditions ↗	Different billing unitPrice details ↗
Less than 1 GB for direct Batch upload; larger files via fetch URLfile limit	Not collected	Usage pricing $0.30 / audio hourBatch transcription · Speechmatics APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricing $0.30 / audio hourAgent transcription · Speechmatics API$0.005 / audio minuteAgent STT Build/Ship · LiveKit InferenceRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	WAV 16 kHz mono signed16, Raw PCM 16 kHz mono signed16 little-endianoutput formats	Usage pricing $0.011 / 1,000 charactersText input · Speechmatics APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗
Not collected	Not collected	Usage pricingNot collected	Different billing unitPrice details ↗

* Media models show their native limits. A shared context window includes both input and output tokens.

Original currency and billing unit, without currency conversion. Rates are dated snapshots; open the conditions for tiers, promotions and endpoint restrictions.How to read the data

Catalog coverage

Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.

See what is being reviewed