Score Speech

This features requires a Premium Subscription Run in Postman: Score Speech

The Score Speech API scores spontaneous, open-ended speech. Unlike Score Text — which scores a known, read-aloud script — Score Speech has no reference text: it transcribes what the speaker actually said and scores it for pronunciation, fluency, grammar, vocabulary, and coherence on the IELTS, PTE, Speechace, TOEIC, and CEFR scales. It can also check whether the answer is relevant to a prompt, and detect the language the speaker used.

For read-aloud scripted text use Score Text; for a single word, letter, or non-word use Score Word.

Scoring modes

Capability	Turn it on with	What it adds to the response
Language scoring	(default — always on)	The transcript, plus pronunciation, fluency, grammar, vocabulary, and coherence subscores on all five scales.
Detailed feedback	include_ielts_feedback=1	grammar, vocab, and coherence nodes with sub-metrics, errors, and feedback messages.
Relevance	relevance_context="<prompt>"	speech_score.relevance.class — TRUE or FALSE.
Language detection	detect_dialect=1 (warn) or enforce_dialect=1 (error)	detected_dialect.lang_id, or a hard error when the spoken language differs from the scoring dialect.

Request Format

The endpoint you use depends 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

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, en-gb, fr-fr, fr-ca, es-es, es-mx
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.

Request Examples

Example	Request Body Parameters	When to use
A. Language scoring	user_audio_file=answer.wav include_ielts_feedback="1"	Score a spontaneous answer for pronunciation, fluency, grammar, vocabulary, and coherence with detailed feedback.
B. Relevance	user_audio_file=answer.wav relevance_context="Describe how travel has changed over time and why."	Also check the answer is on-topic for the question or prompt.
C. Language detection	user_audio_file=answer.wav detect_dialect="1" (or enforce_dialect="1")	Flag — or reject — an answer spoken in a different language than the scoring dialect.

Response Examples

A. Language scores

{
  "status": "success",
  "quota_remaining": -1,
  "speech_score": {
    "transcript": "Yes, I do. Travel today is vastly different than what it used to be. In the past, the traveler had little idea about what to expect when they arrived at their destination. These days, the internet connects our world in many ways previous generation could only dream about. We can instantly review destination information and make travel arrangements. Also, in the past, people could only travel by land or sea. Traveling was often long and unsafe.",
    "word_score_list": [
      {
        "word": "Yes",
        "quality_score": 93,
        "quality_class": "pass",
        "phone_score_list": [
          {
            "phone": "y",
            "stress_level": null,
            "extent": [
              76,
              85
            ],
            "quality_score": 98.66666666666667,
            "word_extent": [
              0,
              1
            ],
            "sound_most_like": "y"
          },
          {
            "phone": "eh",
            "stress_level": 1,
            "extent": [
              85,
              91
            ],
            "quality_score": 81,
            "stress_score": 100,
            "predicted_stress_level": 1,
            "word_extent": [
              1,
              2
            ],
            "sound_most_like": "eh"
          },
          {
            "phone": "s",
            "stress_level": null,
            "extent": [
              91,
              100
            ],
            "quality_score": 99.33333333333333,
            "word_extent": [
              2,
              3
            ],
            "sound_most_like": "s"
          }
        ],
        "ending_punctuation": ",",
        "syllable_score_list": [
          {
            "phone_count": 3,
            "stress_level": 1,
            "letters": "yes",
            "quality_score": 93,
            "stress_score": 100,
            "predicted_stress_level": 1,
            "extent": [
              76,
              100
            ]
          }
        ]
      },
      "... (75 more)"
    ],
    "ielts_score": {
      "pronunciation": 8.5,
      "fluency": 8.5,
      "grammar": 7,
      "coherence": 7,
      "vocab": 7,
      "overall": 7.5
    },
    "pte_score": {
      "pronunciation": 90,
      "fluency": 90,
      "grammar": 67,
      "coherence": 66,
      "vocab": 69,
      "overall": 78
    },
    "speechace_score": {
      "pronunciation": 95,
      "fluency": 97,
      "grammar": 78,
      "coherence": 77,
      "vocab": 79,
      "overall": 85
    },
    "toeic_score": {
      "pronunciation": 190,
      "fluency": 190,
      "grammar": 160,
      "coherence": 160,
      "vocab": 160,
      "overall": 170
    },
    "cefr_score": {
      "pronunciation": "C2",
      "fluency": "C2",
      "grammar": "B2",
      "coherence": "B2",
      "vocab": "B2",
      "overall": "C1"
    },
    "grammar": {
      "overall_metrics": {
        "length": {
          "score": 4,
          "level": "mid"
        },
        "lexical_diversity": {
          "score": 8,
          "level": "high"
        },
        "grammatical_accuracy": {
          "score": 8,
          "level": "high"
        },
        "grammatical_range": {
          "score": 5,
          "level": "mid",
          "message": "Your response has less grammatical range than most advanced speakers. To improve, you should use a wider range of phrasal and clausal structures and verb-argument constructions.",
          "noun_phrase_complexity": {
            "score": 1,
            "level": "low",
            "message": "Your response lacks noun phrase complexity. You should use richer modifiers in noun phrases by using adjectives, relative clauses, prepositional phrases, non-finite elements, determiners, and demonstratives."
          },
          "noun_phrase_variation": {
            "score": 4,
            "level": "mid"
          },
          "verb_construction_variation": {
            "score": 7,
            "level": "mid"
          },
          "adverb_modifier_variation": {
            "score": 9,
            "level": "high"
          }
        }
      },
      "errors": [
        {
          "category": "STYLE",
          "message": "Did you mean 'different from'? 'Different than' is often considered colloquial style.",
          "span": [
            44,
            48
          ],
          "matched_text": "than",
          "replacements": [
            "from"
          ]
        }
      ]
    },
    "vocab": {
      "overall_metrics": {
        "lexical_diversity": {
          "score": 10,
          "level": "high"
        },
        "word_sophistication": {
          "score": 9,
          "level": "high"
        },
        "word_specificity": {
          "score": 6,
          "level": "mid",
          "message": "Your response uses more general words than most advanced speakers. To improve, you should aim to learn and use verbs, nouns, and adjectives more specific to the meaning you wish to convey."
        },
        "academic_language_use": {
          "score": 1,
          "level": "low",
          "message": "Your response is low on use of academic words. You should learn and use some academic language in your responses to improve."
        },
        "collocation_commonality": {
          "score": 8,
          "level": "high"
        },
        "idiomaticity": {
          "score": 6,
          "level": "mid"
        }
      }
    },
    "coherence": {
      "overall_metrics": {
        "lexical_density": {
          "score": 10,
          "level": "high"
        },
        "basic_connectives": {
          "score": 8,
          "level": "high",
          "examples": [
            "and",
            "or"
          ]
        },
        "causal_connectives": {
          "score": 10,
          "level": "high"
        },
        "negative_connectives": {
          "score": 5,
          "level": "mid",
          "message": "Great Job! Your response used negative connectives which added contrast to your argument. See the list of some of the negative connectives used.",
          "examples": [
            "or"
          ]
        },
        "pronoun_density": {
          "score": 4,
          "level": "mid"
        },
        "adverb_diversity": {
          "score": 10,
          "level": "high"
        },
        "verb_diversity": {
          "score": 10,
          "level": "high"
        }
      }
    },
    "fluency": {
      "segment_metrics_list": [
        {
          "segment": [
            0,
            3
          ],
          "duration": 0.975,
          "articulation_length": 0.65,
          "syllable_count": 3,
          "correct_syllable_count": 3,
          "correct_word_count": 3,
          "word_count": 3,
          "speech_rate": 3.076923076923077,
          "articulation_rate": 4.615384615384615,
          "syllable_correct_per_minute": 184.6153846153846,
          "word_correct_per_minute": 184.6153846153846,
          "all_pause_count": 2,
          "all_pause_duration": 0.325,
          "mean_length_run": 0.325,
          "max_length_run": 0.37,
          "all_pause_list": [
            [
              113,
              114
            ],
            [
              142,
              173.5
            ]
          ],
          "ielts_score": {
            "pronunciation": 8.5,
            "fluency": 7.5,
            "grammar": 4,
            "coherence": 4,
            "vocab": 4
          },
          "pte_score": {
            "pronunciation": 90,
            "fluency": 79,
            "grammar": 20,
            "coherence": 20,
            "vocab": 20
          },
          "speechace_score": {
            "pronunciation": 95,
            "fluency": 86,
            "grammar": 44,
            "coherence": 44,
            "vocab": 44
          },
          "toeic_score": {
            "pronunciation": 190,
            "fluency": 170,
            "grammar": 50,
            "coherence": 50,
            "vocab": 50
          },
          "cefr_score": {
            "pronunciation": "C2",
            "fluency": "C1",
            "grammar": "A1",
            "coherence": "A1",
            "vocab": "A1"
          }
        },
        "... (6 more)"
      ],
      "overall_metrics": {
        "segment": [
          0,
          76
        ],
        "duration": 25.59,
        "articulation_length": 21.75,
        "syllable_count": 123,
        "correct_syllable_count": 114,
        "correct_word_count": 70,
        "word_count": 76,
        "speech_rate": 4.8065650644783116,
        "articulation_rate": 5.655172413793103,
        "syllable_correct_per_minute": 267.2919109026964,
        "word_correct_per_minute": 164.126611957796,
        "all_pause_count": 13,
        "all_pause_duration": 3.84,
        "mean_length_run": 1.5535714285714286,
        "max_length_run": 3.66,
        "all_pause_list": [
          [
            113,
            114
          ],
          [
            142,
            205
          ],
          "... (11 more)"
        ]
      },
      "fluency_version": "0.7",
      "ielts_subscore_version": "0.4"
    },
    "asr_version": "0.17"
  },
  "version": "9.17"
}

B. Relevance

{
  "status": "success",
  "quota_remaining": -1,
  "speech_score": {
    "transcript": "Yes, I do. Travel today is vastly different than what it used to be. In the past, the traveler had little idea about what to expect when they arrived at their destination. These days, the internet connects our world in many ways previous generation could only dream about. We can instantly review destination information and make travel arrangements. Also, in the past, people could only travel by land or sea. Traveling was often long and unsafe.",
    "word_score_list": [
      {
        "word": "Yes",
        "quality_score": 93,
        "quality_class": "pass",
        "phone_score_list": [
          {
            "phone": "y",
            "stress_level": null,
            "extent": [
              76,
              85
            ],
            "quality_score": 98.66666666666667,
            "word_extent": [
              0,
              1
            ],
            "sound_most_like": "y"
          },
          {
            "phone": "eh",
            "stress_level": 1,
            "extent": [
              85,
              91
            ],
            "quality_score": 81,
            "stress_score": 100,
            "predicted_stress_level": 1,
            "word_extent": [
              1,
              2
            ],
            "sound_most_like": "eh"
          },
          {
            "phone": "s",
            "stress_level": null,
            "extent": [
              91,
              100
            ],
            "quality_score": 99.33333333333333,
            "word_extent": [
              2,
              3
            ],
            "sound_most_like": "s"
          }
        ],
        "ending_punctuation": ",",
        "syllable_score_list": [
          {
            "phone_count": 3,
            "stress_level": 1,
            "letters": "yes",
            "quality_score": 93,
            "stress_score": 100,
            "predicted_stress_level": 1,
            "extent": [
              76,
              100
            ]
          }
        ]
      },
      "... (75 more)"
    ],
    "relevance": {
      "class": "TRUE"
    },
    "ielts_score": {
      "pronunciation": 8.5,
      "fluency": 8.5,
      "grammar": 7,
      "coherence": 7,
      "vocab": 7,
      "overall": 7.5
    },
    "pte_score": {
      "pronunciation": 90,
      "fluency": 90,
      "grammar": 67,
      "coherence": 66,
      "vocab": 69,
      "overall": 78
    },
    "speechace_score": {
      "pronunciation": 95,
      "fluency": 97,
      "grammar": 78,
      "coherence": 77,
      "vocab": 79,
      "overall": 85
    },
    "toeic_score": {
      "pronunciation": 190,
      "fluency": 190,
      "grammar": 160,
      "coherence": 160,
      "vocab": 160,
      "overall": 170
    },
    "cefr_score": {
      "pronunciation": "C2",
      "fluency": "C2",
      "grammar": "B2",
      "coherence": "B2",
      "vocab": "B2",
      "overall": "C1"
    },
    "grammar": {
      "overall_metrics": {
        "length": {
          "score": 4,
          "level": "mid"
        },
        "lexical_diversity": {
          "score": 8,
          "level": "high"
        },
        "grammatical_accuracy": {
          "score": 8,
          "level": "high"
        },
        "grammatical_range": {
          "score": 5,
          "level": "mid",
          "message": "Your response has less grammatical range than most advanced speakers. To improve, you should use a wider range of phrasal and clausal structures and verb-argument constructions.",
          "noun_phrase_complexity": {
            "score": 1,
            "level": "low",
            "message": "Your response lacks noun phrase complexity. You should use richer modifiers in noun phrases by using adjectives, relative clauses, prepositional phrases, non-finite elements, determiners, and demonstratives."
          },
          "noun_phrase_variation": {
            "score": 4,
            "level": "mid"
          },
          "verb_construction_variation": {
            "score": 7,
            "level": "mid"
          },
          "adverb_modifier_variation": {
            "score": 9,
            "level": "high"
          }
        }
      },
      "errors": [
        {
          "category": "STYLE",
          "message": "Did you mean 'different from'? 'Different than' is often considered colloquial style.",
          "span": [
            44,
            48
          ],
          "matched_text": "than",
          "replacements": [
            "from"
          ]
        }
      ]
    },
    "vocab": {
      "overall_metrics": {
        "lexical_diversity": {
          "score": 10,
          "level": "high"
        },
        "word_sophistication": {
          "score": 9,
          "level": "high"
        },
        "word_specificity": {
          "score": 6,
          "level": "mid",
          "message": "Your response uses more general words than most advanced speakers. To improve, you should aim to learn and use verbs, nouns, and adjectives more specific to the meaning you wish to convey."
        },
        "academic_language_use": {
          "score": 1,
          "level": "low",
          "message": "Your response is low on use of academic words. You should learn and use some academic language in your responses to improve."
        },
        "collocation_commonality": {
          "score": 8,
          "level": "high"
        },
        "idiomaticity": {
          "score": 6,
          "level": "mid"
        }
      }
    },
    "coherence": {
      "overall_metrics": {
        "lexical_density": {
          "score": 10,
          "level": "high"
        },
        "basic_connectives": {
          "score": 8,
          "level": "high",
          "examples": [
            "and",
            "or"
          ]
        },
        "causal_connectives": {
          "score": 10,
          "level": "high"
        },
        "negative_connectives": {
          "score": 5,
          "level": "mid",
          "message": "Great Job! Your response used negative connectives which added contrast to your argument. See the list of some of the negative connectives used.",
          "examples": [
            "or"
          ]
        },
        "pronoun_density": {
          "score": 4,
          "level": "mid"
        },
        "adverb_diversity": {
          "score": 10,
          "level": "high"
        },
        "verb_diversity": {
          "score": 10,
          "level": "high"
        }
      }
    },
    "fluency": {
      "segment_metrics_list": [
        {
          "segment": [
            0,
            3
          ],
          "duration": 0.975,
          "articulation_length": 0.65,
          "syllable_count": 3,
          "correct_syllable_count": 3,
          "correct_word_count": 3,
          "word_count": 3,
          "speech_rate": 3.076923076923077,
          "articulation_rate": 4.615384615384615,
          "syllable_correct_per_minute": 184.6153846153846,
          "word_correct_per_minute": 184.6153846153846,
          "all_pause_count": 2,
          "all_pause_duration": 0.325,
          "mean_length_run": 0.325,
          "max_length_run": 0.37,
          "all_pause_list": [
            [
              113,
              114
            ],
            [
              142,
              173.5
            ]
          ],
          "ielts_score": {
            "pronunciation": 8.5,
            "fluency": 7.5,
            "grammar": 4,
            "coherence": 4,
            "vocab": 4
          },
          "pte_score": {
            "pronunciation": 90,
            "fluency": 79,
            "grammar": 20,
            "coherence": 20,
            "vocab": 20
          },
          "speechace_score": {
            "pronunciation": 95,
            "fluency": 86,
            "grammar": 44,
            "coherence": 44,
            "vocab": 44
          },
          "toeic_score": {
            "pronunciation": 190,
            "fluency": 170,
            "grammar": 50,
            "coherence": 50,
            "vocab": 50
          },
          "cefr_score": {
            "pronunciation": "C2",
            "fluency": "C1",
            "grammar": "A1",
            "coherence": "A1",
            "vocab": "A1"
          }
        },
        "... (6 more)"
      ],
      "overall_metrics": {
        "segment": [
          0,
          76
        ],
        "duration": 25.59,
        "articulation_length": 21.75,
        "syllable_count": 123,
        "correct_syllable_count": 114,
        "correct_word_count": 70,
        "word_count": 76,
        "speech_rate": 4.8065650644783116,
        "articulation_rate": 5.655172413793103,
        "syllable_correct_per_minute": 267.2919109026964,
        "word_correct_per_minute": 164.126611957796,
        "all_pause_count": 13,
        "all_pause_duration": 3.84,
        "mean_length_run": 1.5535714285714286,
        "max_length_run": 3.66,
        "all_pause_list": [
          [
            113,
            114
          ],
          [
            142,
            205
          ],
          "... (11 more)"
        ]
      },
      "fluency_version": "0.7",
      "ielts_subscore_version": "0.4"
    },
    "asr_version": "0.17"
  },
  "version": "9.17"
}

C. Language detection

{
  "status": "success",
  "quota_remaining": -1,
  "speech_score": {
    "transcript": "I love winter vacation because I enjoy the cold air and the snow.",
    "word_score_list": [
      {
        "word": "I",
        "quality_score": 38,
        "quality_class": "fail",
        "phone_score_list": [
          {
            "phone": "ay",
            "stress_level": 1,
            "extent": [
              14,
              26
            ],
            "quality_score": 37.75,
            "stress_score": 100,
            "predicted_stress_level": 0,
            "word_extent": [
              0,
              1
            ],
            "sound_most_like": "ih",
            "child_phones": [
              {
                "extent": [
                  14,
                  23
                ],
                "quality_score": 50.333333333333336,
                "sound_most_like": "iy"
              },
              {
                "extent": [
                  23,
                  26
                ],
                "quality_score": 0,
                "sound_most_like": "hh"
              }
            ]
          }
        ],
        "syllable_score_list": [
          {
            "phone_count": 1,
            "stress_level": 1,
            "letters": "i",
            "quality_score": 38,
            "stress_score": 100,
            "predicted_stress_level": 0,
            "extent": [
              14,
              26
            ]
          }
        ]
      },
      "... (12 more)"
    ],
    "ielts_score": {
      "pronunciation": 4.5,
      "fluency": 5.5,
      "grammar": 5,
      "coherence": 6,
      "vocab": 4,
      "overall": 0
    },
    "pte_score": {
      "pronunciation": 23,
      "fluency": 40,
      "grammar": 30,
      "coherence": 52,
      "vocab": 20,
      "overall": 10
    },
    "speechace_score": {
      "pronunciation": 48,
      "fluency": 60,
      "grammar": 53,
      "coherence": 68,
      "vocab": 46,
      "overall": 0
    },
    "toeic_score": {
      "pronunciation": 80,
      "fluency": 110,
      "grammar": 90,
      "coherence": 120,
      "vocab": 50,
      "overall": 0
    },
    "cefr_score": {
      "pronunciation": "A1+",
      "fluency": "A2+",
      "grammar": "A2",
      "coherence": "B1",
      "vocab": "A1",
      "overall": "A0"
    },
    "score_issue_list": [
      {
        "source": "overall",
        "status": "warning",
        "short_message": "response_too_short",
        "detail_message": "The response is less than 20 words."
      }
    ],
    "fluency": {
      "segment_metrics_list": [
        {
          "segment": [
            0,
            13
          ],
          "duration": 4.14,
          "articulation_length": 3.41,
          "syllable_count": 18,
          "correct_syllable_count": 2,
          "correct_word_count": 0,
          "word_count": 13,
          "speech_rate": 4.347826086956522,
          "articulation_rate": 5.278592375366569,
          "syllable_correct_per_minute": 28.985507246376812,
          "word_correct_per_minute": 0,
          "all_pause_count": 6,
          "all_pause_duration": 0.73,
          "mean_length_run": 0.48714285714285716,
          "max_length_run": 0.95,
          "all_pause_list": [
            [
              26,
              27
            ],
            [
              116,
              179
            ],
            "... (4 more)"
          ],
          "ielts_score": {
            "pronunciation": 4.5,
            "fluency": 5.5,
            "grammar": 5,
            "coherence": 6,
            "vocab": 4
          },
          "pte_score": {
            "pronunciation": 23,
            "fluency": 40,
            "grammar": 30,
            "coherence": 52,
            "vocab": 20
          },
          "speechace_score": {
            "pronunciation": 48,
            "fluency": 60,
            "grammar": 53,
            "coherence": 68,
            "vocab": 46
          },
          "toeic_score": {
            "pronunciation": 80,
            "fluency": 110,
            "grammar": 90,
            "coherence": 120,
            "vocab": 50
          },
          "cefr_score": {
            "pronunciation": "A1+",
            "fluency": "A2+",
            "grammar": "A2",
            "coherence": "B1",
            "vocab": "A1"
          }
        }
      ],
      "overall_metrics": {
        "segment": [
          0,
          13
        ],
        "duration": 4.14,
        "articulation_length": 3.41,
        "syllable_count": 18,
        "correct_syllable_count": 2,
        "correct_word_count": 0,
        "word_count": 13,
        "speech_rate": 4.347826086956522,
        "articulation_rate": 5.278592375366569,
        "syllable_correct_per_minute": 28.985507246376812,
        "word_correct_per_minute": 0,
        "all_pause_count": 6,
        "all_pause_duration": 0.73,
        "mean_length_run": 0.48714285714285716,
        "max_length_run": 0.95,
        "all_pause_list": [
          [
            26,
            27
          ],
          [
            116,
            179
          ],
          "... (4 more)"
        ]
      },
      "fluency_version": "0.7",
      "ielts_subscore_version": "0.4"
    },
    "detected_dialect": {
      "lang_id": "de"
    },
    "asr_version": "0.17"
  },
  "version": "9.17"
}

Response fields

Overall language scores

The API transcribes the audio and rates it on five rubrics, each with an overall score and subscores for pronunciation, fluency, grammar, vocabulary, and coherence:

• speechace_score — 0 to 100

• ielts_score — 0 to 9.0

• pte_score — 10 to 90

• cefr_score — A0 to C2

• toeic_score — 0 to 200

See the scoring rubrics guide to interpret them. Pronunciation and fluency fields are the same as in Score Text.

Grammar feedback

Returned in the grammar node when include_ielts_feedback=1. Each sub-metric has a score (1–10), a level (low / mid / high), and — when the score is low — a message explaining how to improve.

Parameter	Description
grammar.overall_metrics.length	The sufficiency of the response length in words to demonstrate the necessary grammatical range.
grammar.overall_metrics.lexical_diversity	The degree of variation in syntactic structures such as diversity in verbs, adjectives and adverbial modifiers.
grammar.overall_metrics.grammatical_accuracy	The degree of grammatical inaccuracies in the response. A list of grammatical errors with suggested replacements is returned in the grammar.errors node when this index is low.
grammar.overall_metrics.grammatical_range	The degree of grammatical range demonstrated in the response. This score is further broken down into 4 additional sub-indices: noun_phrase_variation noun_phrase_complexity verb_construction_variation adverb_modifier_variation
grammar.overall_metrics.grammatical_range.noun_phrase_variation	The degree of variation in structure of noun phrases such as the number and types of modifiers used in the response.
grammar.overall_metrics.grammatical_range.noun_phrase_complexity	The degree of complexity of noun phrases such as the richness of adjectives, relative clauses, prepositional phrases, nonfinite elements, determiners, and demonstratives used in the response.
grammar.overall.metrics.grammatical_range.verb_construction_variation	The degree of variation in verbal structures such as the number and types of verb structural elements used in the response.
grammar.overall.metrics.grammatical_range.adverb_modifier_variation	The degree of variation in types of adverbs or adverb phrases to modify clauses, verbs, and adjectives used in the response.

The grammar.errors node lists individual grammatical errors:

key	Description
category	The type of error such as; STYLE, GRAMMAR, COLLOCATION, CONFUSED_WORDS
message	A descriptive message of the error. The message may refer to words within the evaluated text and include suggested replacements within the ... markup tags.
span	The [begin, end] indices of the matched text in characters.
matched_text	The matched text where the error was found.
replacements	An array of zero or more suggested replacements where applicable.

Vocabulary feedback

Returned in the vocab node when include_ielts_feedback=1.

Parameter	Description
vocab.overall_metrics.lexical_diversity	The degree of word diversity in the response.
vocab.overall_metrics.word_sophistication	The degree of use of advanced, less common vocabulary in the response.
vocab.overall_metrics.word_specificity	The degree of use of specific (less general) verbs, nouns, and adjectives which are specific to the meaning being conveyed.
vocab.overall_metrics.academic_language_use	The degree of use of academic language in the response.
vocab.overall_metrics.collocation_commonality	The degree of use of advanced word combinations.
vocab.overall_metrics.idiomaticity	The degree of use of idiomatic language.

Coherence feedback

Returned in the coherence node when include_ielts_feedback=1.

Parameter	Description
coherence.overall_metrics.lexical_density	The degree of use of content words within the response.
coherence.overall_metrics.basic_connectives	The degree and variety of basic connectives within the response. A list of most overused basic connectives is included.
coherence.overall_metrics.causal_connectives	The degree and variety of causal connectives within the response. A list of most overused causal connectives is included.
coherence.overall_metrics.negative_connectives	The degree and variety of negative connectives within the response. A list of most used negative connectives is included.
coherence.overall_metrics.pronoun_density	The degree of use of pronouns within the response.
coherence.overall_metrics.adverb_diversity	The degree and variety of adverbs within the response. A list of most overused adverbs is included.
coherence.overall_metrics.verb_diversity	The degree and variety of verbs within the response. A list of most overused verbs is included.

Relevance

Pass relevance_context with the question or topic and the API judges whether the transcript is on-topic, returning the result in speech_score.relevance.class:

• TRUE — the response is relevant to the context.

• FALSE — the response is not relevant; an error message is also returned.

• Too similar — if the response merely repeats the prompt, an error indicates it is too similar to the relevance_context.

Field	Description
transcript	The speech-to-text transcript of what the user has said.
speechace_score	An overall score on a scale of 0 to 100, in addition to subscores for: Fluency, Pronunciation, Grammar, Vocabulary, Coherence.
ielts_score	An overall score on an IELTS scale of 0 to 9.0, in addition to subscores for: Fluency, Pronunciation, Grammar, Vocabulary, Coherence.
pte_score	An overall score on a PTE scale of 10 to 90, in addition to subscores for: Fluency, Pronunciation, Grammar, Vocabulary, Coherence.
cefr_score	An overall score on CEFR scale of A0 to C2, in addition to subscores for: Fluency, Pronunciation, Grammar, Vocabulary, Coherence.
toeic_score	An overall score on an TOEIC scale of 0 to 200, in addition to subscores for: Fluency, Pronunciation, Grammar, Vocabulary, Coherence.
relevance.class	TRUE or FALSE indicating whether the response was relevant given the relevance_context passed as input to the API.

Language detection

Language detection compares the spoken language against the scoring dialect:

• detect_dialect=1 — lenient. The score is unaffected; the detected language is returned under detected_dialect.lang_id (as in the C. Language detection example above).

• enforce_dialect=1 — strict. If the detected language differs from the dialect, the API returns a hard error so you can zero the score. Setting enforce_dialect=1 implies detect_dialect=1.

Enforced-mismatch error:

{
  "status": "error",
  "short_message": "non_dialect_language_detected",
  "detail_message": "The audio file contains speech in 'de' language different from dialect 'en-us'.",
  "version": "9.17"
}