https://github.com/wellwelwel/easy-audio-to-srt
🎙️ Easily convert audio files into SRT subtitles for free and using AI locally (no token required).
https://github.com/wellwelwel/easy-audio-to-srt
Last synced: 3 months ago
JSON representation
🎙️ Easily convert audio files into SRT subtitles for free and using AI locally (no token required).
- Host: GitHub
- URL: https://github.com/wellwelwel/easy-audio-to-srt
- Owner: wellwelwel
- License: unlicense
- Created: 2025-01-19T12:39:22.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-02-06T10:53:23.000Z (9 months ago)
- Last Synced: 2025-04-03T13:51:14.841Z (7 months ago)
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 14
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
README
# 🎙️ Easy Audio to SRT
Easily convert audio files into SRT subtitles for free and using AI locally (no token required).
---
## Usage
```sh
# Transcribing audio files (Portuguese)
sh transcribe .wav
# Translating srt files to English
sh translate .srt
```
---
## Requirements
- [**Docker**](https://www.docker.com/get-started/)
- [**WSL**](https://learn.microsoft.com/pt-br/windows/wsl/install) (for **Windows** users)
> [!IMPORTANT]
>
> - The **Docker** image is pre-configured to use the largest **OpenAI** model available (turbo). For lighter models, check the [available models](https://github.com/openai/whisper?tab=readme-ov-file#available-models-and-languages) and change it in the [./Dockerfile](./Dockerfile) before executing the scripts.
> - Change the primary language (`pt`) in the [./docker-compose.yml](./docker-compose.yml) `transcribe` command.
> - Change the output translation language (`en`) in the [./translate_srt.py](./translate_srt.py) file.
---
## Links
- 📘 [**Whisper** (**OpenAI**) documentation](https://github.com/openai/whisper)
- 📘 [**Googletrans** documentation](https://github.com/ssut/py-googletrans)