Skip to content
@adventists-ai

Adventists AI

Open voice models that hear how you speak: DuplexJev, Sophon-Realtime.

Adventists AI

Open voice models that hear how you speak.

We build the listening and speaking layers for full-duplex voice agents: knowing when a person has finished, when they want to cut in, and what their tone, stress and laughter mean. Our voice stack already runs in 300+ AI hardware products.

Projects

What it is Status
DuplexJev Speech decision model for voice agents: turn-taking, barge-in, emotion, stress, laughter and more, read from audio in one forward pass (10 decisions in ~0.09 s). #1 on public paralinguistic benchmarks (LISTEN, StressTest, MSPB). 32B and 4B, served with vLLM. Open weights · paper · demo
Sophon-Realtime Open full-duplex voice model that hears your tone and speaks with one: laughs, sighs and stresses words when the conversation calls for it. #1 among open full-duplex models on VoiceBench (82.8) and Big Bench Audio (81.8%). Tag and Flash builds run on one GPU with vLLM-Omni; OpenAI GPT-Live compatible Live mode. Open weights · HF · ModelScope · pip install sophon-realtime
heteronym-bench TTS heteronym reading benchmark (English / Japanese): test sets, automatic judges and baselines. Open

Links

DuplexJev is joint work with Zhejiang University and the University of Virginia.

Pinned Loading

  1. duplexjev duplexjev Public

    DuplexJev-32B and DuplexJev-4B: speech decision models for full-duplex voice agents. Typed single-token readout from a frozen speech LLM, served with vLLM. Try it: api.adventists.cn/duplexjev

    Python 153 4

  2. heteronym-bench heteronym-bench Public

    TTS heteronym reading benchmark (English / Japanese): test sets, automatic judges, validation and baselines

    Python 1

Repositories

Showing 10 of 11 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…