{"id":"tyger","slug":"tyger","name":"TYGER","orgId":"ninenine-six","family":"tyger","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/nine_nine_six/status/2110762625198129447","hfRepo":null,"modalities":["audio"],"aliases":["TYGER","tyger s2s","tyger s2s agent","ninenine six tyger","nine nine six tyger"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-17","announced":"2026-10-15","blurb":"NineNineSix's open full-duplex voice model, with the TYGER S2S agent. It listens to the mic and its own speech output together and every 80ms decides whether to speak, hold off or backchannel.","api":"none","openWeights":"yes","params":{"text":"14M-parameter controller on a frozen Nemotron speech-recognition model","source":"Secondary post, not stated by the lab","unsure":true},"facts":[{"label":"Focus","value":"Full-duplex voice turn-taking (speak, hold off or backchannel every 80ms)"},{"label":"Includes","value":"TYGER S2S agent"},{"label":"Weights","value":"Hugging Face"},{"label":"Code","value":"Open source, with a demo"}],"sources":[{"kind":"lab","title":"NineNineSix announcement on X","url":"https://x.com/nine_nine_six/status/2110762625198129447","date":"2026-10-15"}],"firstBenchmark":null},"organization":{"id":"ninenine-six","name":"NineNineSix","slug":"ninenine-six","country":null,"url":null,"color":"#11110F","mark":"N"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 15, 2026; no independent results yet.","lead":"As of Oct 22, 2026, TYGER is pending benchmarks on isitsota: announced Oct 15, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}