JhonatanAiT14

🎤 dictate.sh - Quick and Easy Speech Transcription

📖 Overview

dictate.sh provides quick and efficient speech transcription for users on Apple Silicon. This application uses advanced machine learning techniques for fast speech recognition, enabling users to convert speech into text seamlessly. With its simple setup, anyone can start talking and transcribing in no time.

🚀 Getting Started

To begin using dictate.sh, follow these steps:

Download the Application
You need to visit the Releases page to download the latest version of dictate.sh.
Install Prerequisites
Make sure you have the following requirements:
- A Mac with Apple Silicon.
- Python version 3.10 or higher.
- uv installed on your machine.
- Microphone access granted to your terminal application.
Set Up Your Environment
If you do not have Python or uv installed, you can use a package manager like Homebrew to install them:
```
brew install python
pip install uv
```

📥 Download & Install

To get started, visit the Releases page and download the latest version of dictate.sh. After downloading, follow the instructions to set it up on your machine.

🎤 How to Use

Once you have dictate.sh installed, you can easily run it from your terminal. Here’s how:

Run the Speech Transcription
Open your terminal and navigate to the folder containing dictate.sh. Run the application using:
```
uv run stt.py
```
Using Intent Analysis
If you want to enable intent analysis, simply add the --analyze flag:
```
uv run stt.py --analyze
```
Using Different ASR Models
You can choose a different ASR model by using the --model flag:
```
uv run stt.py --model mlx-community/Qwen3-ASR-1.7B-8bit
```
List Audio Devices
To see all available audio input devices on your system, run:
```
uv run stt.py --list-devices
```
Select a Specific Audio Device
If you want to use a specific audio input device, use the --device option:
```
uv run stt.py --device 3
```

🛠️ Requirements

Before using dictate.sh, ensure that your system meets the following requirements:

Operating System: macOS on Apple Silicon.
Python Version: 3.10 or higher.
Tools: uv must be installed.
Permissions: Grant microphone access to your terminal.

🌟 Features

Low-Latency Transcription: Uses machine learning for fast speech recognition.
Voice Activity Detection: Automatically detects when you are speaking, ensuring accurate transcription.
Intent Analysis: Optional feature for analyzing the intent behind your speech.
Live Terminal Interface: Provides real-time status updates, transcripts, and statistics.
Offline Functionality: Works without internet connection after downloading required models.

📊 Troubleshooting

If you encounter issues while running dictate.sh, check the following:

Ensure you have the correct Python version installed.
Confirm that uv is properly set up on your system.
Make sure your microphone is functioning and has permission in terminal settings.

For additional support or to report issues, visit our GitHub repository and create an issue.

🔗 Learn More

Explore additional resources and documentation in the GitHub repository to enhance your understanding and usage of dictate.sh.

Remember, you can always return to the Releases page to check for the latest updates.