https://github.com/malkiii/transcript-generator

A Streamlit app that converts audio files to text using the OpenAI's Whisper model, generating accurate transcripts in .txt, .srt, and .vtt formats.
https://github.com/malkiii/transcript-generator

groq openai python speech-to-text streamlit subtitles transcript whisper

Last synced: 5 months ago
JSON representation

A Streamlit app that converts audio files to text using the OpenAI's Whisper model, generating accurate transcripts in .txt, .srt, and .vtt formats.

• Host: GitHub
• URL: https://github.com/malkiii/transcript-generator
• Owner: malkiii
• License: mit
• Created: 2025-02-02T10:09:06.000Z (11 months ago)
• Default Branch: master
• Last Pushed: 2025-06-22T00:25:48.000Z (7 months ago)
• Last Synced: 2025-06-22T01:27:00.195Z (7 months ago)
• Topics: groq, openai, python, speech-to-text, streamlit, subtitles, transcript, whisper
• Language: Python
• Homepage: https://transcript-generator.streamlit.app
• Size: 73.2 KB
• Stars: 3
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# 🎙️ Transcript Generator App

[![Preview](./.streamlit/preview.png)](https://transcript-generator.streamlit.app)

Transcript Generator is a [Streamlit](https://streamlit.io/) application that generates transcripts from audio files. The application utilizes the OpenAI `whisper-large-v3-turbo` model for speech recognition to convert speech to text with common formats (.txt, .srt, .vtt) and high accuracy.

## Local Setup

1. Clone the repository using Git or Github CLI.

2. Create a virtual environment (Optional).

3. Install the required dependencies:

   ```sh

   pip install -r requirements.txt

   ```

4. Rename [secrets.example.toml](./.streamlit/secrets.example.toml) file to `secrets.toml` and add your streamlit [secrets](https://docs.streamlit.io/develop/concepts/connections/secrets-management).

5. Run the application by pressing the Run button if you're using the VSCode [Code Runner](https://marketplace.visualstudio.com/items?itemName=formulahendry.code-runner) extension, or manually using:

   ```sh

   python -m streamlit run streamlit_app.py

   ```

## License

This project is licensed under the MIT License. See the [LICENSE](./LICENSE) file for details.