Skip to content

sersavan/speech-to-text-openai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 

Repository files navigation

Script Overview

The script converts speech from audio file to text using the OpenAI API. It handles audio file splitting, sends parts to OpenAI for transcription, combines the text, and optionally creates summaries and timestamps. Supported file types include mp3, mp4, mpeg, mpga, m4a, wav, and webm.

Step 1: Install Python and Libraries

  1. Install Python:

    • macOS: Open Terminal and run:
      brew install python
    • Windows: Download and install from Python website, check "Add Python to PATH".
  2. Install Libraries:

    pip install pydub openai

Step 2: Get an OpenAI API Key

  1. Sign up and log in at OpenAI.
  2. Generate a new API key in your dashboard.

Step 3: Set API Key

macOS:

  1. Open Terminal.
  2. Edit your shell profile:
    nano ~/.bash_profile
  3. Add:
    export OPENAI_API_KEY='your_openai_api_key'
  4. Save and apply changes:
    source ~/.bash_profile

Windows:

  1. Open Command Prompt.
  2. Run:
    setx OPENAI_API_KEY "your_openai_api_key"
  3. Restart Command Prompt.

Step 4: Run the Script

  1. Save the script as transcribe.py.
  2. Open Command Prompt or Terminal, navigate to the script directory.
  3. Run:
    python transcribe.py path_to_your_audio_file
    For Python 3, use:
    python3 transcribe.py path_to_your_audio_file

Example:

python transcribe.py audio.m4a

Optional Parameters

  • --sum: Create a summary.
  • --time: Include timestamps.

Example:

python transcribe.py audio.m4a --sum --time