{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T20:43:40.889Z","data":{"recordId":"wsa_zuv5hswteqk5","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:51:38.871Z","detectedPublishedAt":"2026-10-08T11:36:06.000Z","rights":"original"}],"claims":[{"id":"17c392d8-c6e5-4e04-a68b-266ecb12ac1e","kind":"capability","statement":"The model supports Arabic dialects and Modern Standard Arabic transcription.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"Voxtral Mini 4B Realtime Arabic is a streaming speech-to-text model for **Arabic dialects and Modern Standard Arabic**.","rights":"original"}}]},{"id":"4376aca1-11cb-4800-8ea3-c2ad049cae9c","kind":"capability","statement":"It is designed to handle code-switching between languages within a conversation.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"It is designed to handle challenging real-world audio and **code-switching**, where speakers alternate between languages within the same conversation.","rights":"original"}}]},{"id":"b6e1bc21-d05e-4c97-a654-6a42ba81f69f","kind":"capability","statement":"It processes 16 kHz audio and produces text as audio arrives.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"It processes 16 kHz audio through a causal audio encoder and language decoder, producing text as audio arrives.","rights":"original"}}]},{"id":"046f26a8-0609-4e75-814b-71526058d8b6","kind":"availability","statement":"The model can be used with vLLM or Transformers.","citations":[{"source":1,"supportProbability":0.9,"supports":true,"quote":{"text":"The model is co-developed with the Ministère de la Transition Numérique et de la Réforme Administrative (MTNRA) under the umbrella of the strategic partnership signed between Mistral and Morocco in January 2026 as a sovereign AI asset.","rights":"original"}}]},{"id":"3df98dfd-da75-4153-9221-efd81a59b3fa","kind":"recommendation-relevant","statement":"At a configured transcription delay of 480 ms, it achieves an average CER of 8.82% across seven Arabic benchmarks.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"At a configured transcription delay of **480 ms**, the model achieves an average Character Error Rate (CER) of **8.82%** across seven Arabic benchmarks.","rights":"original"}}]},{"id":"8093c895-c328-40f2-930e-27ed50b806fc","kind":"deployment","statement":"The model is licensed under the Apache 2.0 License.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0.txt).","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}