liuhuayong/x-ollama-voice-mac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
x-ollama-voice-mac project
9 Commits 1 Branch 0 Tags 510 KiB
Python 100%
63afec1eab
Go to file
Andy Peatling 63afec1eab
Update README.md
2023-12-27 20:45:13 -08:00
.gitignore Update gitignore 2023-12-27 13:51:38 -08:00
assistant.png Mac compatible code 2023-12-27 13:51:24 -08:00
assistant.py Update readme and slow down text prompts. 2023-12-27 14:47:00 -08:00
assistant.yaml Mac compatible code 2023-12-27 13:51:24 -08:00
LICENSE Initial commit 2023-12-27 13:20:33 -08:00
README.md Update README.md 2023-12-27 20:45:13 -08:00
requirements.txt Mac compatible code 2023-12-27 13:51:24 -08:00

README.md

ollama-voice-mac

A completely offline voice assistant using Mistral 7b via Ollama and Whisper speech recognition models. This builds on the excellent work of maudoin by adding Mac compatibility with various improvements.

Screenshot 2023-12-27 at 3 53 03 PM

Installing and running

  1. Install Ollama on your Mac.
  2. Download the Mistral 7b model using the ollama pull mistral command.
  3. Download an OpenAI Whisper Model (base works fine).
  4. Clone this repo somewhere.
  5. Place the Whisper model in a /whisper directory in the repo root folder.
  6. Make sure you have Python and Pip installed.
  7. For Apple silicon support of the PyAudio library you'll need to install Homebrew and run brew install portaudio.
  8. Run pip install -r requirements.txt to install.
  9. Run python assistant.py to start the assistant.

Improving the voice

You can improve the quality of the voice by downloading a higher quality version. These instructions work on MacOS 14 Sonoma:

  1. In System Settings select Accessibility > Spoken Content
  2. Select System Voice and Manage Voices...
  3. For English find "Zoe (Premium)" and download it.
  4. Select Zoe (Premium) as your System voice.