backchannel
Release v0.3.6

Any provider, every agent.

Backchannel v0.3.6 completes OpenAI support: the briefing and strategic-signals agents now route by provider like everything else, and batch transcription gains OpenAI audio models.

Download Read quickstart GitHub release

Download Backchannel v0.3.6

These unsigned open-source builds are delivered through the authenticated Backchannel portal. An approved Backchannel account is required; no GitHub identity or repository membership is required.

The Windows and Linux bundles include ffmpeg. On macOS, voice calibration and compressed audio imports still need ffmpeg on PATH.

Windows

Windows x64

For Windows 10 or later on 64-bit Intel or AMD processors.

  1. Download Backchannel-windows-x64-v0.3.6.zip.
  2. Unzip it and run Backchannel.exe.
  3. If SmartScreen appears, choose More info, then Run anyway.
Open v0.3.6 downloads
macOS

macOS Apple Silicon

For Apple Silicon Macs. Intel macOS builds are not included in this release.

  1. Download Backchannel-macos-arm64-v0.3.6.zip.
  2. Unzip it and move Backchannel.app wherever you keep apps.
  3. Right-click Backchannel.app and choose Open the first time.
Open v0.3.6 downloads
Linux

Linux x64

A portable bundle for 64-bit Intel or AMD Linux systems.

  1. Download Backchannel-linux-x64-v0.3.6.tar.gz.
  2. Extract it with tar -xzf Backchannel-linux-x64-v0.3.6.tar.gz.
  3. Run Backchannel/Backchannel.
Open v0.3.6 downloads

What changed

v0.3.6 is a focused follow-up to v0.3.5 for teams running OpenAI models.

Briefing and Strategic Signals on any provider

Both agents previously called Gemini regardless of the configured model, so OpenAI selections failed with a "model not found" error after the call. They now route by the model's provider, with structured output on both paths.

Actionable briefing errors

When a briefing does fail, the status now explains the cause and remedy instead of showing a raw provider error dump.

OpenAI batch transcription

GPT Audio 1.5 and the cost-efficient GPT Audio Mini join the batch transcription options, sending diarized segment audio through Chat Completions audio input. OpenAI's GPT-5.6 text models do not accept audio, so they are deliberately not offered for transcription.

First-run notes

NeedWhat to do
Release access Use the email and password for your approved Backchannel recipient account.
Provider key Follow the guided setup on first launch, or add a key later in Admin -> API Keys. Calls will not start until the transcription model has a usable credential.
Voice calibration Works out of the box on Windows and Linux. On macOS, install ffmpeg and make sure it is on PATH before enrolling your voice.
Upgrading Quit the old version from the tray before starting the new one. Session data is stored per-user and shared by every version. The Admin About tab shows a what's-new notice after upgrading.
Desktop launch Backchannel opens a dedicated local app window in your default browser when it supports app windows, otherwise it uses a standard browser tab. It remains available from the system tray or menu bar.
Docker Check out the v0.3.6 source tag and rebuild Compose to run the same release through containers.

Start with the desktop app or self-host the stack

Both paths run Backchannel on your machine. Choose the desktop bundle for the fastest start, or Compose for maximum control.

Download v0.3.6 Compare setup paths View source