# TYGER model sizes and sources

> TYGER is NineNineSix's speech decision model, built on NVIDIA Nemotron 3.5 streaming ASR 0.6B. It scores audio in 80 ms frames.

Updated 2026-11-04 (Australia/Adelaide)

By NineNineSix · Released: 2026-10-17 · OPEN

A decision model for speech. It listens to the microphone and your text-to-speech at the same time and keeps deciding whether to speak, keep listening, yield or drop in an "mm-hm", scoring audio in 80 ms frames streamed in 320 ms hops. Built for full-duplex voice agents, with an open-source agent (tyger-s2s) on top.

## Facts

- Base: NVIDIA Nemotron 3.5 streaming ASR 0.6B
- Licence: OpenMDW-1.1
- Works with: Any LLM and TTS (maker's claim)

## Claims and sources



## Links

- [Source: Hugging Face](<https://huggingface.co/nineninesix/tyger>)
- [Source: Announcement](<https://x.com/defoemark/status/2111306095591670263>)
- [Source: Voice agent](<https://github.com/nineninesix-ai/tyger-s2s>)

## Related projects

### Full-duplex voice agent

[Full-duplex voice agent](<https://decisionmodels.ai/projects#project-tyger-s2s>)

[Source: nineninesix-ai/tyger-s2s](<https://github.com/nineninesix-ai/tyger-s2s>)

A browser voice agent where the [TYGER](<https://decisionmodels.ai/models/tyger>) decision model is the ears: it transcribes you and decides when you've finished, when you've cut in, and when to say "mm-hm", while an LLM writes the replies.

- Creator: NineNineSix

- Stars: 53

- Licence: Apache-2.0

- Model: [TYGER](<https://decisionmodels.ai/models/tyger>)

- Tags: voice, agent