Sophon-Realtime 32B Flash

Released
2026-11-08
Last refreshed
2026-11-19
Status
Researched today
Open sourceCommercial use: permitted

Sophon-Realtime 32B Flash is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.

Adventists AI releases · 6 in the last 12 monthsChangelog →
Specifications
Released
2026-11-08
Specialization
speech-to-speech
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

Adventists AI develops full-duplex conversational speech models.

Website
Pricing

No tracked provider pricing is available yet.

About

Sophon-Realtime 32B Flash is Adventists AI’s full-duplex voice model build. It listens while speaking, supports interruptions and expressive speech, and provides public weights under Apache 2.0. The Flash pipeline drafts responses early.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Audio

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.