# Speechmatics — API Agent Score

> Score: 66/100 (Grade: C) | Domain: speechmatics.com | Rubric: 1.0.0 | Checked: July 24, 2026

Speechmatics scored 66/100 (C), classified "partially-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/speechmatics)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 66/100 (C)
- Classification: partially-ready

## Category Scores

- API Design: 67/100 (C)
- Developer Experience: 59/100 (D)
- Agent Discovery: 97/100 (A+)
- Agent Understanding: 61/100 (C)
- Agent Usability: 53/100 (D)

## Check Results

### API Design

- [warn] Schema coverage & depth — 0/21 (0%) enum-like params are realized as constrained types (not bare strings). Investigated: sdk 79%.
- [pass] Example coverage — Code samples in 3 language(s) across docs (top: shell, python, javascript); 1/20 pages have ≥ 2 languages on the same page. Investigated: docs 100%, sdk 100%.
- [fail] Security & governance hygiene — No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Code samples in docs — Code samples in 3 language(s) across docs (top: shell, python, javascript); 1/20 pages have ≥ 2 languages on the same page. Investigated: docs 100%.
- [pass] Description completeness — 131/131 operations carry a description. Investigated: sdk 100%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%.
- [fail] Self-service developer portal — Signup page is sales-gated (contact-sales/request-access language detected). Investigated: docs 0%.
- [fail] Quickstart present — No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%.

### Agent Discovery

- [pass] llms.txt present, valid & comprehensive — llms.txt found at https://docs.speechmatics.com/llms.txt. Investigated: docs 100%, sdk 0%.
- [pass] Docs reachable, not hard auth-gated — All 50 sampled pages are publicly accessible. Investigated: docs 100%.
- [pass] Registry & SDK presence — Indexed on Context7 (websites/speechmatics, 1777 snippets). Investigated: docs 100%, sdk 100%, cli 100%.
- [warn] Crawlable / AEO — Sitemap present (127 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [warn] Agent-navigable, token-efficient docs — 1 of 50 pages have substantive content differences between markdown and HTML (avg 3% missing). Investigated: docs 89%.
- [warn] Machine-readable errors (RFC 9457) — Single base error "null" present, but only 1 subclass found; a richer hierarchy lets consumers catch narrowly. Investigated: sdk 50%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 14 sampled pages — likely a CSR-only docs site. Investigated: docs 0%.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Speechmatics' API program shows strong crawlability and discoverability fundamentals, but partners and their AI agents face meaningful friction in two areas: getting hands-on quickly (no self-service portal or quickstart) and building with confidence (missing runnable collections, idempotency guidance, and agent-readable context files). Prioritising a branded developer portal and executable workspace will close the largest gaps in partner onboarding speed and agent integration reliability.