2026.10.02 Realtime SaaS
Fixes
Fix for English transcription with the Enhanced model: spoken numbers like "ten thousand" were sometimes incorrectly transcribed as "ten zero zero zero".
Updated Orchestrator Version: 2026.09.25+62a2863062+16.2.0
Release Notes
Follow new updates and improvements to Speechmatics.
2026.09.28 Realtime SaaS
Improvements
Improved accuracy and latency for Dutch language with the Enhanced model when processing non-speech audio.
Fixed
Fixed slight accuracy degradation when using ForceEndOfUtterance for the following languages by reverting previous latency reduction: ba, be, bg, bn, ca, cmn, cmn_en, cs, cy, de, el, eo, et, eu, fa, gl, he, hi, hr, hu, ia, id, it, lt, lv, mn, mr, ms, pl, pt, ro, sk, sl, sw, ta, th, tr, ug, uk, ur, vi, yue. Note that ForceEndOfUtterance still continues to work for all languages.
Updated Orchestrator Version: 2026.09.21+8a4b0316ed+16.1.0
2026.09.16 Realtime SaaS
Fixed
Disabled ForceEndOfUtterance latency reduction for Korean (ko) language only due to slight accuracy degradation. ForceEndOfUtterance still continues to work for all languages.
Earlier updates
- 2026.09.11 Realtime SaaSImprovements Improved accuracy for GPU Enhanced English when transcribing recent years, e.g., “2026”. Update to ForceEndOfUtterance to avoid occasional truncating of spoken utterance. Updated Orchestrator Version: 2026.09.07+1f5eba77f2+16.0.0Realtime SaaS
- 2026.09.08 Realtime SaaSNew A new real-time Australia-hosted regional endpoint is now available at au.rt.speechmatics.com for customers who require data processing in Australia. This also provides lower-latency real-time transcription for customers in the region. Batch and real-time processing are now available in Australia. This endpoint is also included in the global.rt.speechmatics.com endpoint for customers who prefer automatic nearest-region routing for latency and don’t require strict data residency. Refer to the Realtime transcription documentation for full details.Realtime SaaS
- 2026.08.20 Realtime SaaSImprovements Reduced the mean and P95 latency between client-triggered ForceEndOfUtterance and when final transcripts arrive. Updated Orchestrator Version: 2026.08.17+8225ca39de+15.19.0Realtime SaaS
- 2026.08.06 Realtime SaaSFixes Fixed recently introduced issue with remove_disfluencies, where punctuation around disfluencies was not being removed. Disfluency tagging (and removal) is currently unavailable for Finnish (fi), Norwegian (no) and Swedish (sv), after being added on Jul 29, 2027. Bug introduced in release version: 2026.07.29 Updated Orchestrator Version: 2026.08.05+3c8ca0561c+15.18.0Realtime SaaS
- 2026.07.29 Realtime SaaSNew Disfluency detection and removal now supports 19 additional languages, including Arabic, Danish, Dutch, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Italian, Japanese, Mandarin, Norwegian, Polish, Portuguese, Russian, Spanish, and Swedish. See the documentation for more details. Updated Orchestrator Version: 2026.07.24+b3c1e3bbc5+15.17.0Realtime SaaS
- 2026.07.20 Realtime SaaSNew A new global endpoint is now available at global.rt.speechmatics.com. This address automatically routes connections to the nearest region, providing the lowest latency and eliminating the need to hard-code specific regional endpoints into your applications. Regional endpoints such as eu.rt.speechmatics.com and us.rt.speechmatics.com remain available for customers with specific data residency requirements. Refer to the Realtime transcription documentation for full details.Realtime SaaS
- 2026.07.15 Realtime SaaSNew Realtime transcript messages (AddTranscript , AddPartialTranscript, and EndOfUtterance) now include a forced flag, allowing clients to identify transcripts generated by a forced end of utterance. See the documentation for more details. Improvements Improved accuracy (reduced deletions at end of utterance) when using ForceEndOfUtterance, with specific values of max_delay. Updated Orchestrator Version: 2026.07.10+d3875410b2+15.15.0Realtime SaaS