Autosub is a utility for automatic speech recognition and subtitle generation. It takes a video or an audio file as input, performs voice activity detection to find speech regions, makes parallel requests to Google Web Speech API to generate transcriptions for those regions, (optionally) translates them to a different language, and finally saves the resulting subtitles to disk. It supports a variety of input and output languages (to see which, run the utility with the argument --list-languages) and can currently produce subtitles in either the SRT format or simple JSON.
- Install ffmpeg.
- Run
pip install autosub.
$ autosub -h
usage: autosub [-h] [-C CONCURRENCY] [-o OUTPUT] [-F FORMAT] [-S SRC_LANGUAGE]
[-D DST_LANGUAGE] [-K API_KEY] [--list-formats]
[--list-languages]
[source_path]
positional arguments:
source_path Path to the video or audio file to subtitle
optional arguments:
-h, --help show this help message and exit
-C CONCURRENCY, --concurrency CONCURRENCY
Number of concurrent API requests to make
-o OUTPUT, --output OUTPUT
Output path for subtitles (by default, subtitles are
saved in the same directory and name as the source
path)
-F FORMAT, --format FORMAT
Destination subtitle format
-S SRC_LANGUAGE, --src-language SRC_LANGUAGE
Language spoken in source file
-D DST_LANGUAGE, --dst-language DST_LANGUAGE
Desired language for the subtitles
-K API_KEY, --api-key API_KEY
The Google Translate API key to be used. (Required for
subtitle translation)
--list-formats List all available subtitle formats
--list-languages List all available source/destination languages
MIT
