Skip to main content

A Python library for analyzing meeting/event video recordings with cloud hosted AI.

Project description

A Python library for analyzing meeting/event video recordings with cloud hosted AI.

Save time and enhance efficiency by using AI to generate summaries, battle cards, meeting minutes, sales arguments and action item lists directly from recordings. Hone your prompt engineering skills to distill the desired information.

Technology

The video recording is transformed into a text transcript using the FFmpeg library and the OpenAI Whisper speech-to-text model. Then, the OpenAI ChatGPT-4 Turbo model analyzes and summarizes the transcript according to the user's prompt. The user interface (UI) is developed with the Tkinter library, part of the standard Python distribution, and styled using the ttkbootstrap library.

Supported languages

From: https://platform.openai.com/docs/guides/speech-to-text/supported-languages

OpenAI lists the languages that exceeded <50% word error rate (WER), which is an industry standard benchmark for speech to text model accuracy.

Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.

Requirements

Install Application

python -m pip install ai-minutes

Install FFmpeg

Mac

brew install ffmpeg

Windows

Follow instructions in this arcticle: https://phoenixnap.com/kb/ffmpeg-windows

Run

python -m ai-minutes

UI themes

Application support UI themes from: https://ttkbootstrap.readthedocs.io/en/latest/themes/

list available themes:

python -m ai-minutes -h

use a theme by giving theme name as an argument:

python -m ai-minutes cyborg

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

summaraize-0.0.tar.gz (12.7 kB view hashes)

Uploaded Source

Built Distribution

summaraize-0.0-py3-none-any.whl (13.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page