Metadata-Version: 2.3
Name: kakitori
Version: 1.0.2
Summary: Audio transcription with speaker diarization using Gemini
Requires-Dist: google-genai>=1.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: python-mpv>=1.0.0
Requires-Dist: questionary>=2.0.0
Requires-Dist: rich>=13.0.0
Requires-Python: >=3.11
Description-Content-Type: text/markdown

# Kakitori

CLI tool for audio recording and transcription with speaker diarization using Google's Gemini Flash.

## Installation

```bash
uv tool install kakitori
```

Requires `mpv` and `pactl`/`ffmpeg` (for recording) installed on your system.

## Configuration

Add your Gemini API key to `~/.config/kakitori/.env`:

```bash
GEMINI_API_KEY=your-api-key-here
```

## Usage

### Record and transcribe

```bash
kakitori record
```

### Transcribe an existing file

```bash
kakitori process recording.mp3
```

### Options

```bash
kakitori process recording.mp3 -o transcript.txt   # save to file
kakitori process recording.mp3 --stdout             # output to stdout
kakitori process recording.mp3 --skip-speaker-id    # skip speaker identification
```

## Output

```
[00:15] John: Hello everyone, welcome to today's meeting.
[00:32] Jane: Thanks for having me. I have some updates to share.
```

## License

MIT
