Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jesse-c/local-audio-toolkit
Some handy tools to do with audio locally.
https://github.com/jesse-c/local-audio-toolkit
large-language-models lm-studio macos side-project whisper
Last synced: 8 days ago
JSON representation
Some handy tools to do with audio locally.
- Host: GitHub
- URL: https://github.com/jesse-c/local-audio-toolkit
- Owner: jesse-c
- Created: 2024-11-28T20:24:45.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2024-11-28T21:08:06.000Z (2 months ago)
- Last Synced: 2025-01-28T20:11:50.430Z (9 days ago)
- Topics: large-language-models, lm-studio, macos, side-project, whisper
- Language: Python
- Homepage:
- Size: 113 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Audio Transcription and Summarization Tool
A command-line tool for transcribing and summarizing audio from various sources including YouTube videos, local MP3 files, and microphone recordings. Uses MLX Whisper for transcription and local LLM for summarization.
## Usage
> [!IMPORTANT]
> Make sure you have LM Studio running locally on port 1234 for the summarization feature to work.
The tool provides these commands:
### List Devices
```bash
uv run python src/main.py list-devices
```
### Transcribe
Record from microphone:
```bash
uv run python src/main.py transcribe record
```
From YouTube:
```bash
uv run python src/main.py transcribe https://youtube.com/watch?v=...
```
From local MP3:
```bash
uv run python src/main.py transcribe path/to/audio.mp3
```
### Summarise
Record from microphone:
```bash
uv run python src/main.py summarise record
```
From YouTube:
```
uv run python src/main.py summarise https://youtube.com/watch?v=...
```
From local MP3:
```
uv run python src/main.py summarise path/to/audio.mp3
```
With custom profile:
```
uv run python src/main.py summarise record --profile "software engineer writing PR description"
```
## Building
1. Clone the repository
2. Install dependencies using `uv`:
```bash
uv sync --dev --all-extras
```
## Testing
Tests can be run using pytest:
```bash
uv run pytest --cov=src tests/
```