An org that ranks OpenAI transcription first streams STT through it, and every ticket names its session dialect (SP95)

Shipped: October 4, 2026 at 6:20 PM UTC
Author: Kamo
Commit: de92e83

transcription model was dropped as ADAPTER_UNSUPPORTED and every streaming STT ticket went to Kamo Speech on CPU. Each catalogue row now names the session (the model rides in the session update), and the ticket answers sessionDialect.

All changes

Like what you see shipping?

All of it arrives in your workspace on its own. Start on the free plan and read this page again in a month.

Start Free Forever View Pricing