backchannel
Windows x64
For Windows 10 or later on 64-bit Intel or AMD processors.
- Download
Backchannel-windows-x64-v0.3.7.zip. - Unzip it and run
Backchannel.exe. - If SmartScreen appears, choose More info, then Run anyway.
Release v0.3.7
Run the agents on your own machine.
The analysis agents can now use a self-hosted OpenAI-compatible server -- Ollama, LM Studio, vLLM -- so the whole pipeline can run on your hardware with no API key from anyone.
Download Backchannel v0.3.7
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-v0.3.7.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-v0.3.7.tar.gz. - Extract it with
tar -xzf Backchannel-linux-x64-v0.3.7.tar.gz. - Run
Backchannel/Backchannel.
What changed
v0.3.7 is a focused follow-up to v0.3.6 for anyone who wants analysis to stay on their own hardware.
Self-hosted text models
A new OpenAI-Compatible entry in the model registry targets any OpenAI-shaped chat server: Ollama, LM Studio, vLLM, or LiteLLM. Set its base URL and model id in Admin -> API Keys, then select it per agent like any other model. Paired with local ONNX transcription, nothing leaves your network.
No credential required
Local servers usually want none, so this provider needs no API key and sends no authorization header at all -- an empty bearer token breaks some servers rather than being ignored. Set one only if your endpoint expects it.
Defaults are unchanged
The base URL resolves from the app setting, then OPENAI_BASE_URL, then the previous default, and applies only to this provider -- a saved Ollama URL can never redirect a genuine OpenAI model. With nothing configured, existing installs behave exactly as before. One caveat: the Privacy First switch still turns the agents off, because it recognizes only the local transcription models.
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 v0.3.7 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.