Windows x64
For Windows 10 or later on 64-bit Intel or AMD processors.
- Download
Backchannel-windows-x64-v0.5.2.zip. - Unzip it and run
Backchannel.exe. - If SmartScreen appears, choose More info, then Run anyway.
v0.5.1 was tagged but never distributed, so this is the first release to carry its work: a Tokens tab that reports what a call cost rather than counting tokens, duplicate transcript entries suppressed on calls that capture both microphone and meeting audio, and bounded analysis replies. Added here, the post-call briefing stops squeezing an item's heading into a narrow column beside its labels.
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.
For Windows 10 or later on 64-bit Intel or AMD processors.
Backchannel-windows-x64-v0.5.2.zip.Backchannel.exe.For Apple Silicon Macs. Intel macOS builds are not included in this release.
Backchannel-macos-arm64-v0.5.2.zip.Backchannel.app wherever you keep apps.Backchannel.app and choose Open the first time.A portable bundle for 64-bit Intel or AMD Linux systems.
Backchannel-linux-x64-v0.5.2.tar.gz.tar -xzf Backchannel-linux-x64-v0.5.2.tar.gz.Backchannel/Backchannel.v0.5.2 supersedes v0.5.1, which was tagged but never distributed, and adds a briefing layout fix on top of it.
In the post-call briefing, each item's title shared a line with its status and speaker labels. In the three-across cards at the bottom - objectives, opportunities, open questions - those labels claimed most of the available width and left a five-word heading wrapping over five lines beside a mostly empty card. The labels now drop to their own line when there is no longer room beside the title. Cards with room to spare are unchanged.
That release was tagged but its desktop bundles were never published, so no installation ran it. Its work arrives here: the Tokens tab reporting cost rather than token counts and including the per-minute live audio bridge that previously showed nothing, suppression of duplicate transcript entries on dual-track calls, bounded analysis replies, lighter processor use during a call, a clearer meeting-audio option before the call, GPT Live Transcribe and Gemini 3.7 Flash, corrected Gemini Flash pricing, and the fix for insights that could be deleted by being merged into themselves.
| 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 -> Connections. Calls will not start until the transcription model has a usable credential; local ONNX transcription needs none. |
| 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 | From this release the app updates itself in place: it verifies the new build's signature first and waits for recording and post-processing to finish before restarting. If you install a build manually instead, quit the old version from the tray first. Session data is stored per-user and shared by every version. A previously configured OpenAI-compatible endpoint is migrated automatically on first launch. 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 v0.5.2 source tag and rebuild Compose to run the same release through containers. |
Both paths run Backchannel on your machine. Choose the desktop bundle for the fastest start, or Compose for maximum control.