Voxta

Hello everyone, Here is part 3 of Gerald, the AI companion Reign is building for Cyberpunk 2077 with Voxta. https://youtu.be/SQTonb7axE8 - Gerald composes a poetic tribute to your loyalty and recites it from the passenger seat It is not out yet. We will post here when it is. Try Voxta: https://voxta

Hello everyone, Here is part 2 of Gerald, the AI companion Reign is building for Cyberpunk 2077 with Voxta. It is not out yet. We will post here when it is. Try Voxta: https://voxta.ai/ Cyberpunk 2077 AI companion vs the NCPD: Gerald's old department wants him back (YouTube)

Hello everyone, Here is a first look at something Reign is building with Voxta: AI companions inside Cyberpunk 2077. - Gerald is a retired NCPD patrol robot with a very dark sense of humour - He hears what you say and answers in his own voice, in character, with replies generated live - He rides alo

Hello everyone, This release brings Skills: memory books, MCP servers and the built-in assistants can provide instructions that a character loads only when the task needs them, and a new Skills Assistant writes them from your documents. The new App Assistant in the right panel opens pages, finds con

Hello everyone, We made a short ad for the Content Hub, and Michaela from Heaven Customer Support took the job. If your AI ever bored you, she has a ticket for that. https://youtu.be/Jm_Nbt_VnRM The hub is where community characters, scenarios and collections live, and you install them in one click

Hello everyone, This is the biggest release yet. The Content Hub is a new way to get content right inside Voxta: browse, search and install characters, scenarios and packs, and share your own with the community. Workspaces give a chat a real folder on disk that the AI can read, write and work in, fr

Hello everyone, Episode five is about 3D avatars, and it is the one we laughed at most while making it. - Characters, Create Character, From VRoid Hub. Link your VRoid Hub account once (a free pixiv login); while VRoid reviews our app you may see an "unverified app" warning, which is expected. - Pic

The featured voices on Voxta Cloud now cost 62 30 credits per 1,000 characters. Your monthly credits cover about twice as much talking with them. You'll find them at the top of the voice picker, marked with a star. Characters set to Automatic already use them. If you picked another voice and like th

Hello everyone, Episode four answers the question we get more than any other about vision: how do I let my character see my screen? - Chat Augmentations, then Voxta Utilities: Vision. It comes with Voxta and is already on; on Voxta Cloud the vision model is set up too. - Switch on Continuous Vision

Hello everyone, Episode three, and this one is about the thing Voxta does that the demo apps going around do not: more than one character in the same chat. Nell from the first two episodes gets company. Gus is a retired trawler captain who comes into her shop most evenings to argue about the weather

Hello everyone, Episode two of the how-to series is up, and it picks up where the first one left off: Nell, the character Sophie made from one sentence, now gets a new picture after every reply. It is one switch in the character's Apps tab. Generate images on, her thumbnail as the reference so every

Hello everyone, We are back to making videos, and this is the first of a new how-to series: short, narrated walkthroughs of one feature at a time, recorded in the app itself. The first one is the AI assisted character creator. Sophie describes a character in one sentence, and Voxta writes the name,

Hello everyone, Since v1.10.0 we have shipped two updates, and this post covers both. They were quality releases, so a good part of what follows is fixes, but three things did grow. Memory books are now something you curate: entries can be marked as validated so a merge cannot touch them, reconcilia

Hello everyone, This is a large one. Characters can now call tools in the middle of a reply, so they can search the web, read a page or drive a device without breaking the conversation. Through MCP, they can also reach the MCP servers you already run, and the chat's own actions are served back out t

Hello everyone, This release is mostly about control and reliability. Local thinking models now have a proper reasoning budget, so you decide how much of the model's effort goes into thinking and how much is left for the reply. Voice activity detection was rebuilt to adapt to your room instead of re

Hello everyone, This one is a consolidation release. Since v1.9.0 we have shipped two updates, and this post covers both. The headline additions are video generation through OpenRouter and Voxta Cloud, Q8 quantization for llama.cpp, and a round of memory work that makes recall sharper and long chats

Hello everyone, This one is packed. Alongside a huge amount of work on memory, transcription accuracy, and VRAM awareness, this release brings three headline additions: voices that can act with real emotion and prosody, video generation in the playground, and characters that build a genuine understa

Hello everyone, We've released Voxta Server v1.8.5. This is a small hotfix primarily for users affected by the broken Animation services in v1.8.4. Fixes Fixed Animation service types not appearing in the UI Fixed Kokoro failing to load the GPU ONNX module Fixed Krea 2 and Qwen Image Edit creating e

Hello everyone, Lisa is a playful kitsune foxgirl with a mischievous personality, expressive ears and tail, and a large collection of animations that make her feel lively and fun to interact with. She’ll tease you, ask questions, demand attention, and do her best to keep things interesting. The atta

Hello everyone, v1.8.4 is primarily a stabilization release, with a lot of work going into memory, prompt caching, form reliability, avatar behavior, and platform fixes. But we still managed to sneak in a few notable new toys: a Character Assistant, scriptable on-screen controls, and a much more pra

Hello everyone, v1.8.2 is a focused follow-up to the big 1.8 drop, and it lands on three fronts: the mobile android app finally becomes a real Voxta client, a first look at ARDY, our new text-to-motion animation module, and a HUD you can actually build and shape yourself. 📱 Voxta Mobile Grows Up Th

Hey everyone! Quick follow-up to the big 1.8.0 drop. This one's a stabilization release - mostly fixes to smooth out the rough edges you and we spotted after launch. Nothing flashy, just a more solid experience across the board. 🎨 Build your own worlds Before the fix list - a quick reminder of what

Voxta v1.8.0 is here - and it's a big one. This is really two releases in one: everything from our 1.7 line rolled together with a huge 1.8 drop on top. It's built around three big ideas: characters you can actually see and animate with full VRM support, a massive scenario authoring and scripting up

Hello everyone, A quick hotfix on top of v1.6.0. This one cleans up the rough edges from the v1.6.0 rollout — HY-Motion now ships with its own dependencies (no more Orpheus workaround), the VaM broken-voice race condition is fixed, F5-TTS no longer crashes on libtorchcodec, and MCP gets several robu

Hello everyone, Voxta v1.6.0 is here. This release is built around three big things: a top-to-bottom UI rework, custom reply suggestions that turn chat into a choose-your-own scene, and the groundwork for HY-Motion - our new module that will let your characters move as you speak to them. On top of t

Hello! We've added Gemma 4 to the cloud. It’s fast, very coherent, and handles long conversations much better. Give it a shot. Fix for "Failed to generate text" Error If you're getting a "VoxtaCloud remote error: Error testing text completion API: VoxtaCloud remote error: {"error":"Failed to generat

Hello everyone, Voxta v1.5.0 is here, and it's a big one! This release marks a major milestone with the introduction of the Voxta Mobile App for Android, lets you stay on the cutting edge of new LLMs with our new llama-cpp Python backend, and brings computer vision to LlamaSharp. On top of that, we'

We're seeing intermittent errors from the default text generation model on Voxta Cloud (Mistral 3.1 24B). It throws errors like: Error testing text completion API: VoxtaCloud remote error: {"error":"Failed to generate text (Error code: qnNu49rbsMawKQbW4ybU8kRJc/k=)"}. Workaround while we fix it Swit

We just dropped the new Elite Dangerous character collection, featuring four pre-configured crew members ready for immediate deployment. These characters work right out of the box with the existing module, utilizing the API to monitor your ship's status, telemetry, and critical events in real-time.

Hello everyone, Voxta v1.4.0 is now available. You can download the latest release at the Voxta Portal. This update introduces an OpenAI-compatible API to use Voxta as a backend, a full Elite Dangerous game integration, and several system fixes. Here is the full list of changes in this build: ✨ New

Hello everyone, Voxta v1.3.2 is now available! This update brings a massive boost to generation speeds with cloud integrations, creates a more dynamic browsing experience with video previews, and refines the actual chat experience with a polished Visual Novel aesthetic. We have also overhauled our d

Hello everyone, Voxta v1.3.1 has arrived! This release is packed with major additions, focusing on a brand-new AI Character Generator, real-time visual feedback for image generation, and a huge expansion of supported AI providers. We’ve also introduced EchoTTS for high-quality voice cloning and the

Hello everyone, Voxta v1.2.0 is now available, bringing several upgrades across functionality, performance, and UI polish. This release introduces a built-in solution for local image generation, improvements to Documents and Collections, and a new way to visualize your configurations. ✨ New Features

Hello everyone, Voxta v1.1.0 is now available. This build brings a new Stage View for your avatar-based chats. When using characters with transparent backgrounds, this creates a visual novel-style layout for your multi-character conversations. We've also added the AssemblyAI module as a new Speech-T

Hello everyone, Voxta v1.0.1 is here, packed with powerful new creative tools for your chats. With this release, we've officially moved out of beta! We've introduced a feature that will fundamentally change storytelling in Voxta. With the new chat.imagine() action, the AI can now generate images bas

Hello everyone, Voxta Beta 152 is now available. This update focuses on major new features for developers, significant UI improvements, and key fixes for AI models. Key Additions This release introduces NuGet packages for custom modules, allowing developers to create and integrate their own AI servi

Some users are experiencing an "access_denied" error when logging into the Voxta Cloud Portal with Patreon. The error states: "Please verify your email address through Patreon before logging in." This issue affects some older Patreon accounts and is caused by a problem with Patreon's email verificat

Hello everyone, Voxta 1.0.0-beta.151 is now available. This release focuses primarily on bug fixes and quality-of-life improvements, with a few new features added. Key additions include the ability to open the diagnostics panel without leaving your chat, settings for different explicit content level

Hello everyone, Voxta 1.0.0-beta.150 is now available. This update introduces significant improvements to core functionality and the user interface. A major highlight is the new installer and updater, which simplifies the process of installing and maintaining the application. You no longer need to m

Hey everyone, The new Voxta 149 Beta is now available. This update focuses on adding significant new features, like support for 3D VRM avatars and AI-assisted document editing, alongside many important UI and backend improvements. ✨ New Features & Major Updates 3D VRM Avatar Support (Experimental):

Tired of your AI just talking about its feelings? In this video, we'll show you how to take the training wheels off and turn this thing into a proper assistant that does REAL work. We're talking about a productivity tool that can write actual code, brainstorm your ideas, and answer complex questions

Hey everyone, Beta 148 is here, and it's packed with quality-of-life updates that make Voxta smoother, smarter, and more intuitive to use! This update focuses on streamlining your workflow with a UI overhaul, major improvements to asset management, and a host of fixes that address your feedback. ✨ U

Hey everyone, Beta 146 is a huge one! This update delivers a massive overhaul to how Voxta manages AI models, giving you unprecedented control and flexibility. We've moved all model settings into presets to make switching between LLMs effortless, introduced a new system to see and manage running AI

Hey everyone, Beta 145 is here, and it's packed! This update brings some big changes, focusing on making Voxta smarter and more useful for different tasks, not just roleplay. We've added reasoning model support, a new Assistant view (think GPT-style chat!) turning Voxta into a serious productivity t

🎙️ New Voice Preview: Orpheus TTS Here's a quick demo of Orpheus — a powerful new premium voice with expressive capabilities and real-time streaming. Available now in the latest Voxta beta! Voices like this help bring your characters to life. Support development and get access to premium features t

Hey everyone! Big news! We're excited to release Voxta Server v1.0.0-beta.143! The star of this update is real-time TTS streaming – hear your characters speak much sooner as the audio generates! Experience more natural conversations as you no longer have to wait for the full audio clip to finish pro

Hey everyone! We’ve been keeping this under wraps for a while, but now that the dust has settled, we’re super excited to finally share something big with you. Our Voxta.ai tech was part of Christie’s first-ever AI-only art auction — Augmented Intelligence — which ran in NYC from February 20 to March

Hey everyone! The new Voxy Desktop Companion beta V18 is here—and it's a big one! Here's what’s new: ✨ Unity 6 Upgrade We’ve upgraded Voxy to Unity 6 for better performance, improved stability, and long-term maintainability. You’ll also get access to newer Unity features going forward. 🖼️ Drag-and-