SpeechmaticsEnhanced

Enhanced

Enhanced is Speechmatics’ accuracy-focused general recognition model. It supports the same features as Standard, with a different accuracy and speed trade-off.

General recognition and language packs

Global language packs cover regional accents. Output locale controls spelling or script, rather than selecting a separate trained model.Speechmatics documentation: Languages and medical coverage

Enhanced can be deployed in a combined all-language GPU image or in smaller language groups. The Standard and Enhanced choices can share a container, while remaining different model choices.Speechmatics documentation: Accessing container images

Practical guidance. A specialist domain model can be more useful than changing a spelling locale. Select the medical release for a supported clinical language, or a bilingual model for a known pair of spoken languages.Speechmatics: Medical model training and language expansion

Specifications & access

Enhanced specifications
DetailValue and conditions
AccessAPI, Provider product
Model identifiersenhanced
API selectorenhancedSpeechmatics documentation: Models
Language selectionOne language or a fixed bilingual or multilingual packSpeechmatics documentation: Languages and medical coverage

Related models

  • Multilingual speech recognition model that follows language changes within a recording.

    Launch date API · Provider product
  • English clinical recognition model trained for medical terminology and fast dialogue.

    Launch date API · Provider product
  • Historical recognition generation that expanded self-supervised training and language coverage.

    Launch date Access not confirmed
  • Bilingual recognition model that transcribes Spanish and English in one stream.

    Launch date API · Provider product
  • General speech recognition model that prioritizes transcription throughput.

    Launch date not confirmedAPI · Provider product