Friends following this account must be exceptionally talented, intelligent, and high-caliber individuals. After all, this account posts daily articles about finance summaries and computer tool sharing—topics that ordinary people would find boring and unfollow long ago.
This article shares another hardcore tool: how to convert a video to text with one click. Specifically, it extracts speech from a video into text. While there are many existing solutions online, what I’m sharing is an automated script—no bulky EXE or ZIP files required.

.
Prerequisites
Ensure you have these two tools installed:
ffmpeg
whisper
How the Script Works
The script automates the following steps:
- Use
ffmpeg
to extract audio from the input video. - Process the audio with
whisper
for speech-to-text conversion. - Save the transcribed text to a local TXT file.
No need to worry about:
- Model selection
- Temporary file cleanup
- Manual command assembly
Run the Script
Simply execute:
python D:\program\selfTools\VideoToTxt.py
(You can modify the script path as needed.)

.
Interface Preview
After launching, the interactive UI will appear:
- Select your video file.
- Click the button to start processing.
Download the Script
The script is available via the link below:
🔗 https://pan.quark.cn/s/b6d93b323bc8
Or scan the QR code to download:
0 Comments