autosrt and AutoSub
These are competitors offering alternative approaches to the same task: autosrt uses Google's speech recognition APIs for subtitle generation, while AutoSub provides local speech-to-text alternatives via DeepSpeech or Coqui models, allowing users to choose between cloud-based convenience and on-device privacy/control.
About autosrt
botbahlul/autosrt
A python script COMMAND LINE utility to AUTO GENERATE SUBTITLE FILE (using free Google Speech Recognition API) and TRANSLATED SUBTITLE FILE (using unofficial online Google Translate API) for any video or audio file
Exposes modular class components (Language, SpeechRecognizer, SentenceTranslator, SubtitleFormatter, etc.) for programmatic integration into other Python projects, beyond CLI usage. Leverages FFmpeg for audio extraction and conversion, with configurable concurrency for parallel API requests to optimize processing speed. Supports multiple subtitle formats and 100+ languages, deployable across Windows, Linux, macOS, and Android via Termux.
About AutoSub
abhirooptalasila/AutoSub
A CLI script to generate subtitle files (SRT/VTT/TXT) for any video using either DeepSpeech or Coqui
Extracts audio via FFmpeg at 16kHz sampling rate, then uses pyAudioAnalysis to segment on silence, running inference on each chunk to generate timestamped subtitles. Supports both DeepSpeech and Coqui STT engines with configurable output formats (SRT/VTT/TXT) and subtitle display duration, plus Docker deployment with optional GPU acceleration.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work