https://github.com/mleidel/ovoc
Python GUI using OpenAI audio.speech API to convert text to speech audio file.
https://github.com/mleidel/ovoc
api audio openai python tkinter ttkbootstrap
Last synced: 2 months ago
JSON representation
Python GUI using OpenAI audio.speech API to convert text to speech audio file.
- Host: GitHub
- URL: https://github.com/mleidel/ovoc
- Owner: MLeidel
- License: gpl-3.0
- Created: 2024-03-20T23:28:46.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-03-03T23:17:22.000Z (over 1 year ago)
- Last Synced: 2025-03-04T00:19:41.506Z (over 1 year ago)
- Topics: api, audio, openai, python, tkinter, ttkbootstrap
- Language: Python
- Homepage:
- Size: 4.01 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Ovoc
### OpenAI Voice Desktop App
#### Python - tkinter - openai API
Ovoc uses the OpenAI audio.speech API with several speech parameters
to convert text into speech in the form of an audio file. The quality
of the speech produced is more lifelike than that of previous
text-to-speech technologies.
Explanation of the
[API parameters](https://platform.openai.com/docs/api-reference/audio/createSpeech "openai audio.speech")
```bash
$ python3 ovoc.py
```
#### Required Modules
- openai
- ttkbootstrap
#### Other Requirements
> [OpenAI Key](https://platform.openai.com/api-keys "openai website")
configured in your OS environment as `GPTKEY`.
#### The 'Play' Button
On Linux:
> The program utility 'play' (SoX) plays back the audio file.
On Windows:
> The audio file is played back by the systems media player.
A preferable method for playback would be to open a file manager in the ``.../ovoc/files`
directory and double-click on the various audio files you've created. This will
invoke your system's audio player and allow greater control over playback.
---