Developer and integration guide.
A public reference for teams evaluating Cue: what the desktop product does, where it runs, how to use it responsibly, and which integration surfaces are currently documented.
What Cue does
Cue is a desktop voice AI for macOS and Windows. Press a hotkey, speak, and Cue can transcribe, use the screen context in front of you, and help finish the task in the app you are already using.
It is designed for human-directed desktop workflows. Review any generated output and proposed action, especially when a mistake could cause harm, data loss, or an irreversible result.
Platform and product facts
Cue supports macOS 13+ and Windows 10 version 1809 or later (64-bit). Cue is free to start; Cue Plus is $19.99/month. The current download, pricing, and service terms are published on heycue.io.
For use-case detail, start with the Mac voice typing guide, Windows voice typing guide, or the full workflow library.
Integration status
Cue does not document a public API, SDK, CLI, or MCP server for third-party integration at this time. Do not treat Cue backend endpoints as an integration surface.
For a product, partnership, or technical inquiry, contact Cue instead of attempting programmatic access to its services.
Open evaluation research
Sophon LLC maintains an independent, source-audited map of public benchmarks for voice agents, spoken assistants, speech-enabled tool use, computer action, dictation, latency, and meeting understanding.
Use the practical benchmark guide to choose an evaluation track, or inspect the MIT-licensed data, schema, query CLI, tests, and source audit on GitHub. It is a landscape, not a leaderboard, and does not rank Cue against the projects it includes.
Trust and support
Read Cue's current Privacy Policy and Terms of Service for data handling, third-party services, subscriptions, acceptable use, and responsibilities around AI-generated output. For support, account, billing, privacy, security, or product feedback, use the contact page.
Cue is developed by Sophon LLC. Its published product evidence includes a Google DeepMind Gemmaverse case study.