OpenAI said Thursday that it has updated its ChatGPT desktop app to add support for ChatGPT Voice, which allows users to speak to the app to control AI agents and perform tasks on their computers.

The new feature supports OpenAI’s new family of voice models called ChatGPT-Live, which it launched earlier this month.

ChatGPT VoiceChat works with both GPT Work and codecs, OpenAI said, and can also tap computer skills to explore websites and apps. Also, on MacOS, with Appshots, users can give the app access to things on their screen, including alt-text.

At launch, the smartphone version of ChatGPT Voice featured smoother conversations, with improved interference handling, but was not designed to process smartphones.

Thursday’s desktop update is more capable, allowing users to set up complex commands that involve multiple steps, and respond when ChatGPT needs their input.

In a demo video, OpenAI showed a developer asking ChatGPT to create a new thread, make a pull request, and find the root cause of the bug with a single command.

Users can use ChatGPT Voice in Codex from the iOS app via remote access, the company said.

Anthropic has also updated its voice mode for Claude, which can tap the company’s Opus, Sonnet, and Haiku models to complete tasks in apps like Gmail, Calendar, Slack, Notion, and Canva.