Skip to main content

Single-file unscripted assessment​

Add a file of an audio, and receive a transcription of that audio.This can accetp mp3, wav, flac. Audio data can be processed in 3 different ways:

  • audio_file: @<local_audio_file_path> → (note the ‘@’ for multipart upload of a binary file) allows to send a local audio file to an audio file available online. Make sure the audio file is accessible.
  • audio_data: <base64_data_string> → audio data sent as a string,encoded in base64
Request Body

Audio data can be processed in 3 different ways:

  • audio_file: @<local_audio_file_path> → (note the ‘@’ for multipart upload of a binary file) allows to send a local audio file
  • audio_path: <remote_audio_path_url> → points to a URL path to an audio file available online. Make sure the audio file is accessible.
  • audio_data: <base64_data_string> → audio data sent as a string, encoded in base64
    api_plan string required

    Possible values: [standard, premium]

    return_json boolean required

    Possible values: [true, false]

    audio_file binary required

    Possible values: Value must match regular expression @<local_audio_file_path>;<remote_audio_path_url> ;<base64_data_string>

Responses

Records match query criteria.

Schema
    speakers object[]
  • Array [
    • speaker_id integer
    total_time number
    metrics object
    general_scores object
    elsa object
    eps_score null
    pronunciation_score number
    intonation_score null
    fluency_score null
    grammar_score null
    vocabulary_score null
    cefr object
    overall_cefr null
    pronunciation_cefr string
    intonation_cefr null
    fluency_cefr null
    grammar_cefr null
    vocabulary_cefr string
    other_scores object
    ielts_score null
    toefl_score null
    toeic_score null
    pte_score null
    other_metrics object
    pronunciation object
    advanced_pronunciation_score integer
    fluency object
    words_per_minute null
    words_per_minute_min null
    words_per_minute_max null
    vocabulary object
    total_words_count integer
    unique_words_count integer
    uncommon_words_count integer
    cefr_distribution object[]
  • Array [
    • cefr_level string
    percentage integer
  • ]
    • feedbacks object
    show_transcript boolean
    pronunciation object
    top_errors object[]
  • Array [
    • phoneme string
    count integer
    errors object[]
  • Array [
    • type string
    error_phoneme string
    count integer
    examples object[]
  • Array [
    • text string
    start_index integer
    end_index integer
  • ]
  • ]
  • ]
    • grammar object
    items object[]
  • Array [
  • ]
    • vocabulary object
    top_cefr_words object[]
  • Array [
  • ]
    • utterances object[]
  • Array [
    • utterance_id integer
    start_time number
    end_time number
    start_index integer
    end_index integer
    text string
    result object
    speed_metrics object
    words_per_minute number
    syllables_per_minute number
    phones_per_minute number
    articulated_words_per_minute number
    articulated_syllables_per_minute number
    articulated_phones_per_minute number
    pronunciation_rate_metrics object
    correct_words_per_minute number
    correct_syllables_per_minute number
    correct_phones_per_minute number
    correct_words_ratio integer
    correct_syllables_ratio number
    correct_phones_ratio number
    pausing_metrics object
    pause_ratio number
    pause_ratio_without_initial_sil integer
    pausing_score_percentage null
    initial_silence boolean
    total_time number
    has_speech boolean
    decision string
    nativeness_score number
    nativeness_score_partial number
    ipa string
    intonation_score null
    fluency_score null
    ielts_score null
    words object[]
  • Array [
    • start_index integer
    end_index integer
    start_time number
    end_time number
    word string
    text string
    ipa string
    trans_arpabet string
    nativeness_score integer
    decision string
    phonemes object[]
  • Array [
    • text string
    start_index integer
    end_index integer
    start_time number
    end_time number
    ipa string
    trans_arpabet string
    decision string
    nativeness_score integer
    phoneme_error string
    phoneme_error_arpabet string
    feedback object[]
  • Array [
  • ]
  • ]
    • word_stress object[]
  • Array [
  • ]
  • ]
  • ]
  • ]
    • transcript string
    timeline object[]
  • Array [
    • speaker_id integer
    utterance_id integer
    start_time number
    end_time number
    start_index integer
    end_index integer
  • ]
    • api_version string
    api_plan string
    recording_quality string
    assessment_quality string
    total_time number
    success boolean
Loading...