{"omc_version":"0.1","id":"microsoft-azure-speech-07-2026","name":"Azure Speech 07 2026","provider":"Microsoft","released":null,"licence":{"tag":"Closed weights, API access only","state":"parsed","url":"https://llmap.ai/licenses/proprietary-api"},"url":null,"description":"Azure Speech 07 2026 is Microsoft's proprietary speech-to-text service that turns audio into written words across 25 languages. It performs better than most models on real-world audio like podcasts, meetings and accented speech, though its overall accuracy sits in the middle of the field.","modalities":["audio"],"context_window":null,"capabilities":{"transcription":4.5},"x_llmap_capability_sources":{"transcription":{"suite":"asr-wer","suite_name":"Open ASR WER","rank":2,"of":76,"score":3.81125,"higher_is_better":false,"variant":null}},"relationships":[{"type":"successor-of","id":"microsoft-azure-speech-06-2026"},{"type":"same-family","id":"microsoft-azure-speech-06-2026"}],"card_meta":{"created":"2026-09-14T20:17:55.867Z","created_by":"LLMap pipeline","last_updated":"2026-09-28T20:17:57.457Z","x_llmap_prices_checked":null,"x_llmap_prices_oldest":null,"x_llmap_prices_newest":null,"source":"https://llmap.ai/models/microsoft-azure-speech-07-2026","omc_spec":"https://github.com/openmodelcard/spec"}}