Skip to main content

Accuracy and Language

Transcription:BatchReal-TimeDeployments:All

For more information on the full range of language packs offered by Speechmatics, please refer to the guide on Supported Language Packs.

Accuracy

Speechmatics offers two operating points for transcription:

  • Enhanced - Optimized for the highest accuracy possible.
  • Standard - (Default) Optimized for fast Batch turnaround time.

Note that when transcribing in real-time, latency for both Standard and Enhanced operating points is controlled using the max_delay config option described here.

Note that your choice of Operating Point will impact pricing, as well as the processing cost efficiency for On-Prem customers.

{
  "type": "transcription",
  "transcription_config": {
    "language": "en",
    "operating_point": "enhanced"
  }
}

Output Locale

For the English language pack only, it is possible to specify the spelling rules to be used when generating the transcription, based on the output_locale configuration setting.

The three locales in English that are available are:

  • British English (en-GB)
  • US English (en-US)
  • Australian English (en-AU)

When transcribing in English, it is recommended to specify the locale. If no locale is specified then the spelling may be inconsistent within a transcript.

The following locales are supported for Chinese Mandarin:

  • Simplified Mandarin (cmn-Hans)
  • Traditional Mandarin (cmn-Hant)

The default is Simplified Mandarin.

An example configuration request is below:

{
  "type": "transcription",
  "transcription_config": {
    "language": "en",
    "output_locale": "en-GB"
  }
}

Bilingual Spanish & English

This model is ideal when transcribing Spanish and English in the same media file or stream. Supports all accents and dialects listed under English and Spanish. Requires the domain config to be set as shown below:

{
  "type": "transcription",
  "transcription_config": {
    "language": "es",
    "domain": "bilingual-en"
  }
}