> For the complete documentation index, see [llms.txt](https://api-docs.speechace.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://api-docs.speechace.com/use-cases/automated-language-assessment-with-ai/skills-assessments.md).

# Skills assessments

Some roles need specific, demonstrable skills: clear pronunciation for a phone agent, or the ability to work through a real customer situation. Two endpoints cover these.

## Read-aloud: pronunciation and fluency (score/text)

Give the candidate a short script to read aloud, such as a customer-service line, and score it with [score/text](/api-reference/score-text.md) and `include_fluency=1`. You get pronunciation, intelligibility, and fluency on a known, controlled passage, which isolates delivery from content.

Example script:

> "I'm sorry for the trouble with your order. Let me pull up your account and find the fastest way to fix this."

{% code overflow="wrap" lineNumbers="true" expandable="true" %}

```json
{
  "text_score": {
    "speechace_score": { "pronunciation": 83, "fluency": 78 },
    "cefr_score": { "pronunciation": "B2", "fluency": "B2" }
  }
}
```

{% endcode %}

See [score/text](/api-reference/score-text.md) for the fluency metrics (speech rate, pauses, articulation).

## Situational task (score/task)

Present a task with a defined criteria and outcome and score how well the candidate accomplishes it with [score/task](/api-reference/score-task.md). Choose the `task_type` that matches your scenario (`describe-image`, `retell-lecture`, `answer-question`), supply the model answer or question in `task_context` / `task_question`, and set `include_speech_score=1` to also return pronunciation and fluency.

Example scenario (describe-image):

> "Task: Analyzing and describing a bar chart about electricity generation from renewable and non-renewable sources in different countries."

<pre class="language-json" data-overflow="wrap" data-line-numbers data-expandable="true"><code class="lang-json">{
  "task_score": { 
     "type": "describe-image", 
     "score": 5,
     "transcript": "The bar chart compares electricity generation in five countries in 2020, renewable against fossil fuel. Norway is the clear outlier, producing almost all of its electricity from renewables, while Poland and India rely overwhelmingly on fossil fuels. Germany and the UK sit between them with a fairly even split. Overall the chart shows a sharp divide between a few renewable leaders and the fossil-dependent countries, which suggests policy rather than natural resources drives the mix."     
<strong>       "score_explanation" : "The response accurately describes all key features of the image, including the standout performance of Norway, the heavy reliance on fossil fuels in Poland and India, and the balanced approach in Germany and the UK. It also identifies the major trend of a divide between renewable and fossil-fuel-based electricity generation and offers a logical conclusion that policy, rather than natural resources, influences the energy mix. The response is concise but comprehensive, with no missing elements or inaccuracies.",
</strong>   },
  "speech_score": { "speechace_score": { "pronunciation": 80, "fluency": 75, ..., "overall": 77 } }
}
</code></pre>

For open-ended situational answers with no single correct response (acknowledge, gather details, resolve), use [score/speech](/api-reference/score-speech.md) with `relevance_context` instead, scored the same way as a [screening interview](/use-cases/automated-language-assessment-with-ai/screening-interviews.md).