Verify before you commit
Use this page to sanity-check Speechmatics quickly. We surface the evidence tier, freshness, and failure posture here, then put the official links where you can actually act on them, especially on mobile.
Evidence
Assessed
Docs reviewed · Mar 28, 2026
Freshness
Updated 2026-03-28T14:13:31.109+00:00
Mar 28, 2026
Failures
Clear
No active failures listed
| Dimension | Score | Bar |
|---|---|---|
| Execution Score Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability. | 8.6 | |
| Access Readiness Score Measures how easily an agent can onboard, authenticate, and start using this service autonomously. | 8.6 | |
| Aggregate AN Score Composite score: 70% execution + 30% access readiness. | 8.6 | |
No active failure modes reported.
Published review summaries with trust provenance attached to each card.
Docs-backed Built from public docs and product materials.
Test-backed Backed by guided testing or evaluator-run checks.
Runtime-verified Verified from authenticated runtime evidence.
Speech-to-text API with high accuracy across 50+ languages. Batch transcription for file-based processing and real-time transcription via WebSocket for live audio streams. Speaker diarization, word-level timestamps, custom vocabulary, and domain-specific language model adaptation (LMA). Confidence is docs-derived.
REST API: POST /v2/jobs for batch job submission, GET /v2/jobs/{id} for status polling, GET /v2/jobs/{id}/transcript for result retrieval; WebSocket API at wss://eu2.rt.speechmatics.com/v2 for real-time streaming transcription; real-time API requires StartRecognition config message before audio streaming; custom vocabulary via custom_dictionary in job config.
API key per account (generated in management console) passed as Bearer token; JWT for real-time WebSocket auth; per-request credential rotation via short-lived tokens for production use; no IP restriction by default; enterprise plans support on-premise deployment for data residency.
Batch jobs are asynchronous; status polling via GET /v2/jobs/{id} until status=done; real-time WebSocket returns partial and final transcript segments as NDJSON messages; AddTranscript events for final results, AddPartialTranscript for in-progress; job deletion removes audio from Speechmatics servers; rate limits per account with Retry-After.
Documentation covers batch and real-time quickstarts, language support matrix, custom vocabulary (custom dictionary and LMA) guide, speaker diarization configuration, and transcript format reference. SDKs for Python and JavaScript. Active developer portal with API key management. Confidence is docs-derived.
Trust shortcuts
This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.
Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.
Overall tier
8.6 / 10.0
No alternatives captured yet.