---
title: "Pace vs Cursor Voice"
description: "An evidence-based comparison of Pace and Cursor Voice: fully on-device vs OpenAI Realtime per turn."
canonical: https://heypace.app/compared/cursor-voice/
last-updated: 2026-08-27
---
# Pace vs Cursor Voice

An evidence-based comparison of Pace and Cursor Voice: fully on-device vs OpenAI Realtime per turn.

## Product posture

- **Product:** [Cursor Voice](https://github.com/cursorvoice/cursor-voice)
- **Maintainer:** cursorvoice
- **License:** MIT; open source under MIT
- **Runtime posture:** cloud
- **Speech-to-text:** OpenAI Realtime API
- **Reasoner:** OpenAI Realtime API (gpt-realtime)
- **Text-to-speech:** OpenAI Realtime API (built-in voices)
- **Screen-aware:** Yes

## What the competing product does well

- Barge-in with echo rejection — interrupt the AI mid-response by talking over it.
- On-device wake word ("Hey Cursor") via SFSpeechRecognizer, then cloud Realtime API for the conversation.
- Built-in web_search tool without requiring an API key.

## Where Pace differs

Pace is fully on-device; Cursor Voice round-trips every turn through OpenAI's Realtime API. Cursor Voice has barge-in and wake word — both things Pace lacks. Pace wins on privacy and zero per-turn cost.

This comparison does not claim ratings, market rank, or user-review scores.