OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Chat & Assistants

Ollama Voice Mac

Ollama Voice Mac is a Python-based macOS voice assistant that uses Whisper for speech recognition, Mistral 7B served by Ollama for responses, and a macOS system voice to speak them.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ollama Voice Mac — OpenViST project profile in Chat & Assistants.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a Mac-based voice interface to a locally hosted Mistral model and are prepared to install the models and Python dependencies yourself.

Who it is for

  • Mac users who want to ask questions by voice using a locally hosted language model.
  • People setting up a local speech interface for Ollama chat workflows.

Documented uses

  • Capture spoken input and recognize it with a Whisper model.
  • Send recognized input to a Mistral model served through Ollama.
  • Hear assistant replies through a macOS system voice.
  • Configure speech recognition for another language by selecting a matching Whisper model.
Before you choose

Requirements & limits

The repository is public and lists an AGPL-3.0 license. The documented setup runs on macOS and requires local installation of Ollama, models and Python dependencies.

  • The README describes local, offline operation rather than a hosted assistant.
  • The project uses Whisper for recognition and an Ollama-served Mistral 7B model for responses.
  • Other-language setup requires editing assistant.yaml and using a Whisper model for that language.
  • The assistant is launched from the command line after installing its requirements.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and start the assistant on a Mac

Prepare the documented local dependencies and launch the voice assistant.

Before you start

  • A Mac with Ollama installed
  • Python and Pip
  • A downloaded Whisper model
  • Homebrew and PortAudio for Apple silicon PyAudio support

Steps

  1. Pull the Mistral 7B model with ollama pull mistral.

  2. Clone the repository and place the Whisper model in a /whisper directory at its root.

  3. Install the requirements with the command below.

    Documented command
    pip install -r requirements.txt

  4. Start the assistant with the command below.

    Documented command
    python assistant.py

Expected outcome

The assistant starts with locally hosted Mistral and Whisper components for spoken interaction.

Guide limitations

  • Apple silicon users need Homebrew and PortAudio for PyAudio support.
  • The README's optional premium system-voice instructions are specified for macOS 14 Sonoma.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
apeatling/ollama-voice-mac · Official homepage title · retained in its source language
How we review sourcesSuggest a correction