Score Speech/Open-ended

Run in Postman: Language Scores

Request Format

The endpoint that is to be used will depend on the region of your subscription. For example, for US West, the endpoint is https://api.speechace.co

POST https://api.speechace.co/api/scoring/speech/v9/json

curl --location -g 'https://api.speechace.co/api/scoring/speech/v9/json?key={{speechace_premiumkey}}&dialect=en-us' \
--form 'user_audio_file=@"traveltoday.wav"' \
--form 'include_ielts_feedback=1'

Query Parameters

Parameter
Type
Description

key

String

API key issued by Speechace.

dialect

String

This is the dialect in which the speaker will be assessed. Supported values are "en-us" (US English) and "en-gb" (UK English).

user_id

String

Optional: A unique anonymized identifier (generated by your applications) for the end-user who spoke the audio.

Request Body

Parameter
Type
Description

user_audio_file

File

file with user audio (wav, mp3, m4a, webm, ogg, aiff)

question_info

String

Optional flag: A unique identifier (generated by your application) for the activity or question this user audio is answering.

include_ielts_feedback

String

1 Optional: Includes detailed feedback metrics for Grammar, Vocab, Coherence.

relevance_context

String

Optional: Question Prompt text provided to the user. When this parameter is passed, the relevance of the user audio transcript is evaluated given the relevance_context and a resulting relevance class is returned in .speech_score.relevance.class

pronunciation_score_mode

String

Optional field: Possible values -

  • default: will only penalize pronunciation errors which affect word intelligibility.

  • strict: will penalize prononciation errors even those which do not affect intelligibility resulting in generally lower pronunciation scores.

detect_dialect

String

Optional field: Possible values - 0 | 1

1: will apply language detection and warn if the majority of the response language is different from the intended scoring dialect.

enforce_dialect

String

Optional field: Possible values - 0 | 1

1: will apply language detection and error if the majority of the response language is different from the intended scoring dialect.

Setting enforce_dialect=1 automatically sets detect_dialect=1.

Response Example

Last updated