Varterm Extensions

Cursor / VS Code Extension

Search Varterm TTS in Extensions and flip on Agent Auto-read. Send a prompt, go back to your file, and the reply reads itself when it lands — no parking on the chat panel. One install, every window, zero echo.

Long answers split into parts, so you jump forward past the preamble or back to the line that mattered instead of scrolling the chat. Same engine handles whole files, RFCs, and multi-page docs — playback starts on part one while the rest generates. Editor, selection, and clipboard work the same way.

Cursor installs from Open VSX. VS Code can use the same search or the Marketplace. The .vsix is optional — use it only if search is empty or you want a pinned GitHub build.

Manual file is v0.1.40 from GitHub Releases. To rebuild, see the README Development section in varterm/extensions.

1. Install: Extensions view → search Varterm TTS → click Install (user), not Install Workspace Extension → reload other Cursor windows.
2. Optional .vsix: Command Palette → Extensions: Install from VSIX... → choose the package from GitHub Releases.
3. Run Varterm: Connect only if you use a custom server or token.
4. Click Agent Auto-read in the status bar. A finished reply plays in the focused window only — extra Cursor windows stay quiet. Use play/pause, stop, and jump. Play reads an editor selection if you have one.
5. Run Varterm: Read Clipboard Aloud or Varterm: Read Editor/Selection Aloud for long-form docs and markdown files.

Chrome Extension

Read selected text or entire pages directly in your browser, including long-form articles and markdown-style AI outputs.

1. Install extension and pin it to toolbar.
2. Select text and use the floating button or context menu for long passages and markdown blocks.
3. If testing locally: open `chrome://extensions` and use Load unpacked.

Web App

Use Varterm instantly with no setup for long-form docs, markdown cleanup, and ChatGPT-ready playback.

1. Paste text into the editor.
2. Pick Cloud, Browser, or Offline voice mode.
3. Press play and follow chunk progress for long text.