Sophon-Realtime 4B is out: open-source (Apache-2.0) full-duplex voice AI on one consumer GPU.
Flash-4B: one 24 GB GPU, first audio 0.21 s
Tag-4B: Full-Duplex-Bench 94.3, on par with our 32B
Knows less than 32B: best for companions and local demos.
huggingface.co/adventists-ai…
No GPU? Try Sophon-Realtime in the cloud.
Sign up with an email and get 3 hours of free full-duplex voice chat.
• Tag, Flash and E2E models
• OpenAI Realtime-compatible: point your SDK at it
• Barge-in, back-channels, English & Chinese
api.adventists.ai/console
@ModelScope2022
1
134
Full-duplex voice AI, fully offline on one Mac.
Sophon-Realtime now runs on Apple silicon (MLX). No cloud, no internet.
• Hears your voice directly, no speech-to-text
• Cut in anytime: stops in ~0.1 s
• ~1 s to reply on an M4 Max
github.com/adventists-ai/sop…
@ModelScope2022
1
5
159
Sophon-Realtime v1.2 is out.
• Long replies are now spoken to the end, no cap on speech length.
• New: Flash-4bit — full-duplex voice chat on one 32 GB GPU, ~0.2 s first audio, barge-in + tool calls.
huggingface.co/adventists-ai
github.com/adventists-ai/sop…
1
5
170
Sophon-Realtime v1.1: zero-shot voice cloning in our open full-duplex model.
A few seconds of audio and it talks in that voice, live. No fine-tuning, no restart, one GPU.
Video: my voice from 11 s, then a colleague's from 9 s. Thanks @ModelScope2022!
teapawt.net/ModelScope2022/status/…
Sophon-Realtime v1.1 from Adventists AI @BKJinAI adds zero-shot voice cloning to an open-weights, full-duplex voice model.
Drop a few seconds of someone's voice into model/voices/, set "voice" to its name, and talk to it in that voice in real time. No fine-tuning, no restart, one GPU. Barge-in and laughs still work, and a voice cloned from a clip in one language can speak another.
Available in the Tag and Flash builds on ModelScope. Live mode is a drop-in replacement for the OpenAI GPT-Live API, and an E2E build with 0.21 s to first audio is coming soon.
Please only clone voices you have permission to use. 🤖modelscope.ai/models/Adventi…
Also in the video: Live mode. Sophon hands lookups like weather or news to your own backend, keeps talking, then says the answer. It's a drop-in for the OpenAI GPT-Live API, and we'll open-source the backend framework too.
1
17
Thanks @ModelScope2022 for the feature! Sophon-Realtime v1 is open on ModelScope: it hears your tone and speaks with one.
Talk to it in your browser: modelscope.ai/studios/Advent…
Or self-host on one GPU with vLLM-Omni:
pip install sophon-realtime && sophon-realtime serve
Adventists AI just open-sourced Sophon-Realtime v1 on ModelScope: a full-duplex voice model that hears how you speak, and answers with tone of its own.
• It keeps listening while you talk, answers ~0.4 s after you stop, and stops the moment you cut in
• It laughs, sighs and clears its throat when the conversation calls for it
• #1 among open full-duplex models on VoiceBench (82.8) and Big Bench Audio (81.8%)
• 48% Pass@1 on Full-Duplex-Bench v3 tool calling, ahead of Grok (43%)
Apache-2.0 weights. Built by @BKJinAI and team.
modelscope.ai/collections/Ad…
modelscope.ai/studios/Advent…
1
2
109
Sophon-Realtime v1 is out: an open full-duplex voice model that hears your tone and speaks with one.
It listens while you talk, catches sarcasm and stress, and laughs or sighs when the moment calls for it.
Single live takes, no edits, no speed-up. Open weights, Apache-2.0.
Two builds, each on one GPU with vLLM-Omni:
· Tag: the most expressive voice, ~0.6 s to first audio
· Flash: 0.31 s to first audio, 40 users per GPU
pip install sophon-realtime
github.com/adventists-ai/sop…
3
2
150
Try it in your browser, nothing to install. Thanks @ModelScope2022 for featuring it on the ModelScope homepage.
modelscope.ai/studios/Advent…
1
73
A transcript keeps the words and drops the rest: the anger in "wait, wait, stop", a laugh with no words at all, which name got the stress.
That's what a voice agent needs before it decides to talk. 30 s of what DuplexJev hears:
hf.co/spaces/BitKnight/Duple…
45
Most voice agents decide when to talk with a silence timer. We think they should listen.
DuplexJev hears turn-taking, interruptions, emotion, stress and laughter straight from the audio: 10 decisions in 0.09 s.
2
1
48
On 1,035 paralinguistic test items (LISTEN, StressTest, MSPB) it scores 50.2, ahead of Gemini 3.8 Flash (47.8), Qwen3-Omni (45.0) and GPT-audio (40.9).
Open weights: github.com/adventists-ai/dup…
29


