backchannel
Windows x64
For Windows 10 or later on 64-bit Intel or AMD processors.
- Download
Backchannel-windows-x64-v0.3.5.zip. - Unzip it and run
Backchannel.exe. - If SmartScreen appears, choose More info, then Run anyway.
Release v0.3.5
Errors that explain themselves. Costs you can see.
Backchannel v0.3.5 turns provider failures into actionable messages with retries, refreshes the OpenAI lineup including the GPT-5.6 family, and estimates what each call cost.
Download Backchannel v0.3.5
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.
macOS Apple Silicon
For Apple Silicon Macs. Intel macOS builds are not included in this release.
- Download
Backchannel-macos-arm64-v0.3.5.zip. - Unzip it and move
Backchannel.appwherever you keep apps. - Right-click
Backchannel.appand choose Open the first time.
Linux x64
A portable bundle for 64-bit Intel or AMD Linux systems.
- Download
Backchannel-linux-x64-v0.3.5.tar.gz. - Extract it with
tar -xzf Backchannel-linux-x64-v0.3.5.tar.gz. - Run
Backchannel/Backchannel.
What changed
v0.3.5 focuses on trust: failures explain themselves, dialogs match the app, and costs are visible.
Actionable provider errors
Chat and Enhance Insights now report quota, spending-cap, and API-key failures with the exact remedy instead of a bare server error. Failed Enhance runs show their reason and offer a one-click Retry failed batches.
Summaries that add up
The post-call banner now anchors its numbers: "Final analysis pass: 3 new insights, 7 insights updated - 23 insights total for this session."
Native popups retired
Every confirmation and notice now uses the app's themed dialogs. The browser's raw "localhost says" popups are gone.
Current OpenAI lineup
The GPT-5.6 family (sol, terra, luna) joins the model registry, and OpenAI transcription models (gpt-4o-transcribe, gpt-4o-mini-transcribe) become batch transcription options once a working OpenAI key is added.
Cost visibility
Admin -> About lists every available model with its current pricing, and the post-call Tokens tab estimates cost per model and per session at standard text rates.
First-run notes
| Need | What 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 v0.3.5 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.