dimonier/batch-speech-to-text

Python wrapper for OpenAI's Whisper for processing all audio files in a specified folder and creating raw text + transcript with time stamps

30
/ 100
Emerging

This tool transcribes spoken words from audio and video files into text, helping you convert interviews, lectures, or meetings into written records. You provide one or more media files, and it outputs raw text and optionally a time-coded transcript. It is ideal for researchers, journalists, or anyone needing to analyze spoken content, especially in Russian.

No commits in the last 6 months.

Use this if you need to quickly and accurately convert a collection of audio or video recordings into written Russian text with correct punctuation and case, and optionally with timestamps.

Not ideal if you primarily work with languages other than Russian and require automatic punctuation and case recovery, or if you prefer a graphical user interface over command-line usage.

transcription media-analysis content-creation interview-analysis lecture-notes
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

MIT

Last pushed

Apr 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dimonier/batch-speech-to-text"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.