Plugins With Paid Service Voxta (Virt-A-Mate Plugin)

Highlights​

a floating chat input bar so you can type to the character (great for VR, clutch when voice isn't working), native subtitles with no VAMOverlays dependency (now with a distinct color for /event / /note / /story narration), and screen-share vision so the character can actually see what's on your monitor.

New — Chat input bar​

• Floating chat input bar at the bottom of the view. Type a message, hit Enter or the SEND button, and the character responds. Pressing Enter on an empty field asks the current character to continue speaking.
• Works in VR. Click the input field with your controller laser, VaM's on-screen keyboard pops up, SEND button handles submit because VaM's keyboard Enter doesn't always fire. Separate Vertical Position / Width / Scale sliders for VR.
• Real mic mute. Clicking the mic icon disables the SpeechToText service on your Voxta server via REST — Deepgram actually stops, you actually stop paying for STT while muted.
• Real speaker mute. Clicking the speaker icon disables the TextToSpeech service. Characters still generate text replies and you still see subtitles, but no audio plays.
• State syncs across clients. Mic/speaker toggles go through the server config, so toggling from voxta-talk updates the VaM plugin's icon live (and vice versa).
• Procedural icons (pencil, mic, speaker, paper-plane) drawn at runtime — no external assets needed, crisp in both desktop and VR.
• Slash-command picker. Click the pencil icon for a grid of common commands: /event, /story, /note, /noreply, /context, /summarize, /infer. Click to paste the prefix — caret lands at the end so your next keystroke appends instead of wiping it.
• Reply suggestions. Click "Suggestions…" from the pencil menu and the server returns three reply options (positive / neutral / edgy) that fill the input on click.
• Smart ready state. When chat isn't started yet, the pencil goes dim, the input is greyed out, and clicking the input opens the plugin's Custom UI directly on the Chat tab — so first-time users never get stuck clicking a dead text box.
• Hover feedback on all four bar buttons so you can tell they're clickable.

New — Subtitles​

• Native subtitles overlay. Voxta now renders subtitles directly — no external plugin needed. Character speech in pink, user speech in blue, both fully tweakable.
• Subtitles tab with independent character / user / events text toggles, color pickers, font size (desktop/VR), vertical position (desktop/VR), VR tilt, fade duration, auto-hide toggle + delay, and a preview toggle that shows sample lines side-by-side so you can tune without starting a chat.
• VR-aware: separate font-size and vertical-position sliders for VR so text sits comfortably in your field of view.
• Events & narration color. Special messages from /event, /note, and /story now show in the subtitle overlay in orange — matching how voxta-talk styles them. These were previously invisible in VaM.

New — Vision​

• Share-screen capture. When Voxta continuous-vision is enabled on the server, the plugin now snapshots VaM's render, downscales, and POSTs it so the character has visual context of the scene. Tested end-to-end against Deepgram STT with continuous vision — the model produces accurate scene descriptions (including OCR of on-screen text) and references visual details in its replies.
• Opt-in. Settings → Vision → "Let Character See Screen" toggle is off by default and re-disables on every plugin load (privacy-first). Toggling it flips the server's ComputerVision service via REST, so all capture paths really stop when you turn it off.

New — Chat tab​

• Replay Last Character Message. New button re-voices the last reply through the full audio + subtitle + trigger pipeline — perfect for iterating on subtitle colors / position / fade or audio routing without burning LLM + TTS tokens on a fresh reply. Doesn't add a new turn to chat history.

New — Lipsync​

• Auto-configure on Start Chat. Clicking Start Chat now applies the correct mouth settings to every Person audio target automatically. Default-scene users just get working mouths — no more hunting for the old "Enable Lip Sync" button.
• New Settings tab houses the behavior toggles (auto-lipsync checkbox, manual "Apply Lipsync Now" action) and is where new global tweaks will live going forward.

New — UI polish​

• Connection status field goes green when you're actually connected, white otherwise — at-a-glance health check.
• Uniform tab strip. All tabs share the same pale-blue resting color; the selected tab pops in saturated blue, so your current tab is obvious.
• Subtitles tab layout rebalanced — Text Size moved to the top of the right column.

Fixes​

• Subtitle no longer flickers bare "Catherine:" during inter-sentence silence gaps.
• Subtitle keeps the previous sentence visible through short silence pauses instead of fading to blank and back.
• silence: placeholder AudioUrls (sent when TTS is disabled) no longer error — the playback pipeline now simulates the requested duration and still fires subtitle / state transitions.
• Chat-input canvas registered with VaM's VR pointer system so the bar is actually clickable with a controller laser — previously the canvas rendered fine but clicks silently missed.
• /story narration now displays subtitles even when your scene has no Narrator atom configured (text-only fallback).

Breaking changes — coming from .87​

• VAMOverlays integration removed. Scenes that were routing Voxta subtitles through VAMOverlays's string param will no longer display text via that route. Subtitles are native now. The handful of existing scenes will log harmless warnings about stored subtitle-routing keys on next load; just re-save the scene to clear them.

Migrating old scenes​

If your scene had the older Scripter + VAMOverlays subtitle setup wired up, you'll see two subtitles at once after upgrading: one from Voxta's new native overlay, and one from your Scripter still pushing text into VAMOverlays.

Cleanest fix — just remove VAMOverlays from the scene entirely:

1. Delete the Overlays atom (or remove the VAMOverlays plugin from it).
2. If you have a Scripter snippet that references VAMOverlays (the overlays, setSubtitles, subtitlesColor variables in the Voxta docs example), delete those lines from your Scripter's index.js. Timeline / action routing in the same file can stay — only the overlays-related bits need to go.

After that, subtitles come from Voxta alone and everything is tunable from the Subtitles tab.

v1.3.0 — VaM package #87

Highlights​

A UI overhaul of the plugin's Custom UI plus VR HUD fixes and smaller polish.

New​

• Reorganized plugin Custom UI into 6 focused tabs with color-coded tabs and primary/destructive action buttons
• "Open Plugin UI" HUD button — open the full plugin UI directly from the HUD
• Start/Stop Chat button on the Chat tab, with label reflecting whether it starts a new chat or resumes one
• API Key field masked with bullets and a Clear button
• Package tab made readable
• Chat tab columns swapped — characters on the left, session actions on the right

Fixes​

• VR: Toolbar button now tilts with the HUD, and the main HUD stays visible when the plugin UI is opened
• VR: HUD menu scaling fixed at non-default worldScale
• Character list no longer appears empty on first plugin load
• Bundled resource files are now found when they carry Voxta's version suffix
• "Voxta Active" toggle removed from the HUD quick menu (was redundant with new controls)

🎛 New: Quick-Access HUD Menu​

A new Voxta button on the VaM toolbar opens a quick-access floating panel on the main HUD with a Voxta Active toggle. The plugin's Active state stays in sync between the quick menu, the main plugin UI, and any external triggers.

New storables — last message metadata​

Five new read-only JSONStorableString parameters expose info about the most recent chat message, useful for driving triggers and scene logic from other plugins:

• LastMessageRole — user / assistant / system
• LastMessageScenarioRole — the role as defined in the scenario
• LastMessageSenderId — character/user ID
• LastMessageSenderName — display name
• LastMessageText — the message content

OnMessage trigger now fires on updates​

The OnMessage trigger previously fired only when a new message was received. It now also fires on in-flight message updates (partial/streamed content, edits), so reactive triggers get every state change.

🗨 Improved chat event handling​

Client now handles two additional server events — chatLoadingMessage (while a message is being generated) and chatStarting (session boot) — for smoother session start-up and loading UX.

- Support for Voxta API 2025-11
- Register a label for the Virt-A-Mate Plugin for Voxta
- Register an example snippet in the scenario scripts editor
- Log clearer error on user interaction requests

- Support for Voxta Server v1.0.0-beta.150 (API 2025-08)
- Built-in support for subtitles (VAMOverlays)
- Fix error when inspectorScenarioEventExecuted is displayed

- Auto-configure lip sync button
- Fix error logs for loading and inspector messages
- Better error messages for unauthorized responses

This release is all about increasing stability, plus a few goodies on the server as usual!

Since some of you want to keep the optimization plugins!

This should help for users who did not upgrade VaM recently (you should!)

This builds brings the highly praised F5-TTS and Kokoro text to speech models to Voxta! You can use custom chat backgrounds in scenarios and other goodies, expect some cool scenarios! Also, characters can use scripts (for example, make today's mood change, or dynamically create a different greeting every time). Some of you may like the new Wake Word support, so you can keep Voxy on all the time without wasting speech to text! There are new modules you may like, too: Continuations and Chain Of Thought. They allows characters to reach out when idle and think before answering! You might also want to look at Catherine again, who now boasts some dynamic states and greetings, increasing her diversity. Finally, generate suggestions for when you're out of inspiration!

See Discord for the full build 136 release notes.

VaM specific changes:

- Voxta Server v1.0.0-beta.136 support
- Actions "activates" field support for multi-step action inference
- Use SuperController.OpenURL (new VaM security requirement)
- Removed useless logs