{"omc_version":"0.1","id":"speechmatics-enhanced","name":"Speechmatics Enhanced","provider":"Speechmatics","released":null,"licence":"Commercial API","url":null,"description":"Speechmatics Enhanced is a hosted-only speech-to-text engine that turns audio into written words across 55 languages. It excels on clean, read-aloud English with a very low error rate, but accuracy drops sharply in meetings and on heavily accented speech. No pricing or hosted access is currently available in our data.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":3},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":41,"of":74,"score":5.898571429,"higher_is_better":false,"variant":null}},"relationships":[],"card_meta":{"created":"2026-08-01T22:45:55.861Z","created_by":"LLMap pipeline","last_updated":"2026-08-03T20:17:40.102Z","source":"https://llmap.ai/models/speechmatics-enhanced","omc_spec":"https://github.com/openmodelcard/spec"}}