---
title: "Pace vs Fazm"
description: "An evidence-based comparison of Pace and Fazm: on-device speech vs Deepgram-cloud STT/TTS."
canonical: https://heypace.app/compared/fazm/
last-updated: 2026-08-27
---
# Pace vs Fazm

An evidence-based comparison of Pace and Fazm: on-device speech vs Deepgram-cloud STT/TTS.

## Product posture

- **Product:** [Fazm](https://github.com/mediar-ai/fazm)
- **Maintainer:** mediar-ai
- **License:** MIT; open source under MIT
- **Runtime posture:** hybrid
- **Speech-to-text:** Deepgram Nova-3 (streaming WebSocket)
- **Reasoner:** Claude (via ACP bridge)
- **Text-to-speech:** Deepgram Aura (7 languages)
- **Screen-aware:** Yes

## What the competing product does well

- Controls 300+ macOS apps via the Accessibility API — not screenshots, the structured UI tree.
- Multi-language architecture: Swift desktop + TypeScript ACP bridge + Rust backend.
- Real Chrome session automation — Gmail, Drive, Docs, Sheets, Calendar, WhatsApp.

## Where Pace differs

Fazm uses the Accessibility API for screen understanding (more reliable, more token-efficient than Pace's VLM-screenshot approach). But Fazm's STT and TTS go through Deepgram's cloud despite 'local' marketing. Pace is fully on-device, including speech.

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