> 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/getting-started/how-speechace-scoring-works.md).

# How Speechace scoring works

Speechace scores spoken (and written) language through a small set of endpoints. Which one you use comes down to two things: **whether you provide the expected text**, and **what you want scored**.

### Scripted vs. spontaneous

**Scripted** — you know what the speaker should say and pass it as the reference:

* [score/word](/api-reference/score-word.md) — a single word, letter name, letter sound, or non-word.
* [score/text](/api-reference/score-text.md) — a word, sentence, or passage read aloud; adds fluency, lexical stress, and intonation on request.

**Spontaneous** — there is no reference text, so the API transcribes what was actually said and scores that:

* [score/speech](/api-reference/score-speech.md) — open-ended speech: pronunciation, fluency, grammar, vocabulary, and coherence, plus optional relevance and language detection.
* [score/task](/api-reference/score-task.md) — task achievement: how completely a response fulfills a specific task (describe an image, re-tell a lecture, answer a question).

**Writing**

* [score/writing](/api-reference/score-writing.md) — essays and short written responses.

### What each endpoint scores

<table><thead><tr><th width="170">Endpoint</th><th width="250">You give it</th><th>It returns</th></tr></thead><tbody><tr><td><a href="/api-reference/score-word.md">score/word</a></td><td>One word / letter / non-word + audio</td><td>Word, syllable, and phoneme quality scores</td></tr><tr><td><a href="/api-reference/score-text.md">score/text</a></td><td>Reference text + audio</td><td>Pronunciation — plus fluency, stress, and intonation on request</td></tr><tr><td><a href="/api-reference/score-speech.md">score/speech</a></td><td>Audio (no reference text)</td><td>Transcript + pronunciation, fluency, grammar, vocabulary, coherence (+ relevance, language detection)</td></tr><tr><td><a href="/api-reference/score-task.md">score/task</a></td><td>Task prompt + audio or text</td><td>Task-achievement score, plus the language scores above</td></tr><tr><td><a href="/api-reference/score-writing.md">score/writing</a></td><td>Prompt + written answer</td><td>Task response, grammar, vocabulary, coherence</td></tr></tbody></table>

Every response is mapped to the common [scoring rubrics](/interpreting-results/scoring-rubrics.md) — Speechace, IELTS, PTE, TOEIC, and CEFR — so you can compare levels across activities and tests.

Not sure which one you need? See [Choosing an endpoint](/api-reference/choosing-an-endpoint.md).