backchannel
Windows x64
For Windows 10 or later on 64-bit Intel or AMD processors.
- Download
Backchannel-windows-x64-v0.6.3.zip. - Unzip it and run
Backchannel.exe. - If SmartScreen appears, choose More info, then Run anyway.
Release v0.6.3
Local transcription actually works now.
Run a meeting with a local model on v0.6.1 or v0.6.2 and nothing came out of it: the call recorded, speakers were separated, and not one line of transcript was saved. The bundle was missing files the speech library reads every time it transcribes, and the previous release fixed one missing piece and shipped without the next one. Both are fixed. Nothing is lost either, because the audio is still on disk and re-transcribing rebuilds the transcript from it.
Download Backchannel v0.6.3
These unsigned open-source builds are delivered through the Backchannel download portal. Downloads are open to everyone; no account or GitHub sign-in 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-v0.6.3.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-v0.6.3.tar.gz. - Extract it with
tar -xzf Backchannel-linux-x64-v0.6.3.tar.gz. - Run
Backchannel/Backchannel.
What changed
v0.6.3 is a fix release. Local transcription had never worked in a shipped desktop build; two releases in a row failed at two different layers of the same packaging fault.
The bundle ships the files the speech engine reads
onnx-asr reads data from inside its own package every time it transcribes, and the desktop bundle did not contain it, so every job failed the moment it started. Diarization was unaffected, which is why a call looked like it was working: speakers were being separated the whole time, with nothing to attach to them. The build now fails outright rather than producing a bundle without those files.
Your recordings are recoverable
Audio was always saved correctly, so meetings that produced no transcript are not lost. Open the session, choose Re-transcribe, and the transcript is rebuilt from the recording.
The app no longer claims to be ready when it is not
Readiness only checked whether the speech library could be named, not whether it could run. That check passed in both broken builds, so the app reported transcription as ready and then failed every job in silence. It now proves the engine actually works before saying so, and names the real fault when it does not.
Re-transcribe will not erase a transcript it cannot replace
It deleted the existing transcript before replaying the audio, so a transcriber that could not run turned the button into an erase. It now refuses before touching anything and tells you why.
The release check transcribes before publishing
The gate only confirmed the app started, and a broken build starts perfectly well. That is how both faults reached people. A finished bundle now has to run the speech engine before it can be published.
First-run notes
| Need | What to do |
|---|---|
| Release access | Nothing - downloads are open to everyone; no account or sign-in is required. |
| 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 | An install on v0.5.3 or later updates itself in place, with no account anywhere on the path: it verifies the new build's signature first and waits for recording and post-processing to finish before restarting. After updating, re-transcribe any session that came back empty; the audio is still there. An install on v0.5.2 or earlier will not see this release from inside the app: download the bundle above, quit the old version from the tray, and run the new one. Session data is stored per-user and shared by every version, and the PII Shield stays off until you turn it on in Admin -> Privacy. 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 v0.6.3 source tag and rebuild Compose to run the same release through containers. If you reach the stack by a DNS hostname rather than an IP address or localhost, set BACKCHANNEL_ALLOWED_HOSTS to that name in .env first. |
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.