Voxta

Voxta is an AI companion for people who want a character they can talk to, assign tasks to or use in interactive stories. You choose its personality, voice and optional avatar.

• Voice conversations: Speak with your companion, interrupt its replies and keep memories across conversations; it can examine photos or your screen on request.
• File and coding tasks: It reads, writes and edits workspace files, calls Claude Code or OpenAI Codex for coding work, searches the web and uses MCP tools or custom scripts.
• Interactive stories: Create characters and scenarios with spoken dialogue, images generated locally or in the cloud, and scriptable maps, inventories and HUD widgets.
• Community content: The Content Hub lets you browse and share characters, scenarios and memory books.
• Custom behavior: JavaScript scripting, Python integration, a C# SDK and an API let developers extend conversations and build modules.

Voxta runs as a local server with a browser interface. Windows 10 and 11 support the full desktop app. Linux supports the server and browser interface but lacks some Windows features, including screen capture. There's no macOS or iOS app.

AI processing can run entirely on your hardware, through Voxta Cloud or across both. Cloud processing doesn't require a powerful GPU. Voice choices include ElevenLabs, Fish Audio, Voxta Cloud and local services.

Local models keep conversations on your machine. Requests to Voxta Cloud or third-party APIs leave it; Voxta Cloud doesn't save chat data, while external providers apply their own data policies. Anonymous server telemetry is opt-in and disabled by default.