Pending benchmarksTracking since Oct 17, 2026
Is TYGER state of the art?Pending benchmarks.Announced Oct 15, 2026; no independent results yet.
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.
Announced facts
The details so far
- Lab
- NineNineSix
- Announced
- Oct 15, 2026
- API
- Not yet
- Open weights
- Published
- Parameters
- 14M-parameter controller on a frozen Nemotron speech-recognition modelunsure
- Focus
- Full-duplex voice turn-taking (speak, hold off or backchannel every 80ms)
- Includes
- TYGER S2S agent
- Weights
- Hugging Face
- Code
- Open source, with a demo
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Receipts
Sources
LABNineNineSix announcement on Xx.com/nine_nine_six/status/2110762625198129447 · Oct 15, 2026Tracking continues until an independent board lists it.