FREEDOM251

Freedom251 › AI Video Caption Generators

asub

by asub

Free plan LinuxMacWindows

Visit asub Alternatives

asub's own site

What asub is

asub is a free subtitle generator for Linux, macOS, and Windows. It creates subtitles from audio or video with faster-whisper, detecting the source language automatically or accepting a manual selection. Subtitles can be translated into more than 100 languages through Google Translate without an API key, then written as SRT or WebVTT files. Batch processing handles supported media in a folder while loading the Whisper model once for that batch. Optional WhisperX-powered diarization adds anonymous speaker labels, although overlapping speech can be difficult to process. The software runs on CPU or GPU and offers int8 quantisation for lower-memory systems. Whisper model choices range from tiny to large-v3, with automatic device and compute-type detection when omitted. The project combines faster-whisper, deep-translator with Google Translate, Silero VAD, and optional WhisperX and pyannote diarization models. A Python API covers model loading, transcription, translation, and subtitle writing. asub uses the MIT License and requires Python 3.10 or later. Folder scans cover only the top level, and translation batches may encounter network or rate-limit issues.

Who it suits

asub suits people creating or translating subtitles locally on Linux, macOS, or Windows. It is useful for users who need SRT or WebVTT output, batch processing, or optional speaker labels.

What it does well

  • Free on Linux, macOS, and Windows
  • Translates into 100+ languages without an API key
  • Exports SRT and WebVTT
  • Supports CPU, GPU, and int8 quantisation
  • Offers optional anonymous speaker labels

What to know first

  • Requires Python 3.10 or later
  • Folder scans cover only the top level
  • Translation may face network or rate-limit issues
  • Overlapping speech can challenge diarization

Verdict

asub provides Whisper-based transcription, translation, batch handling, and common subtitle exports at no listed cost. Check its Python requirement and translation or diarization limitations for your workflow.

Facts from asub's own pages

Batch processing
It can process supported media files in a folder, loading the Whisper model once for the batch. · github.com, 12 Oct 2026
Free plan
Yes · github.com, 22 Sept 2026
Hardware
It runs on CPU or GPU and supports int8 quantisation for low-memory setups. · github.com, 12 Oct 2026
Hardware and models
It supports CPU and GPU processing, offers Whisper model choices from tiny to large-v3, and auto-detects device and compute type when omitted. · github.com, 12 Oct 2026
Headquarters
Italy · github.com, 19 Oct 2026
Installation status
The README labels PyPI installation as “once published.” · github.com, 12 Oct 2026
Integrations
The project uses faster-whisper, deep-translator with Google Translate, Silero VAD, and optional WhisperX and pyannote diarization models. · github.com, 12 Oct 2026
Language requirements
The package metadata requires Python 3.10 or later. · github.com, 12 Oct 2026
Languages
It automatically detects the source language or lets users specify it, and translates subtitles into 100+ languages via Google Translate without an API key. · github.com, 12 Oct 2026
License
The software is distributed under the MIT License, which permits use, copying, modification, distribution, sublicensing, and sale subject to its stated conditions. · github.com, 12 Oct 2026
Limits
Folder processing scans only the top level, and translation batches can encounter network or rate-limit issues. · github.com, 12 Oct 2026
Other operating systems
The README gives Linux and macOS shell instructions for setting the Hugging Face token, and the package metadata classifies the software as OS independent. · github.com, 12 Oct 2026
Output formats
It can write subtitles in SRT and WebVTT formats. · github.com, 12 Oct 2026
Purpose
asub generates and translates subtitles from audio or video files using Whisper. · github.com, 12 Oct 2026
Python API
The README provides a Python API for loading a model, transcribing media, translating segments, and writing subtitle files. · github.com, 12 Oct 2026
Speaker identification
Yes · github.com, 22 Sept 2026
Speaker labels
Optional WhisperX-powered diarization adds anonymous speaker labels, and the README notes that overlapping speech can be difficult to handle. · github.com, 12 Oct 2026
Subtitle export
srt and vtt · github.com, 22 Sept 2026
Subtitle formats
It outputs SRT and WebVTT subtitle files. · github.com, 12 Oct 2026
Transcription
It uses faster-whisper and offers automatic language detection or manual source-language selection. · github.com, 12 Oct 2026
Translation
It translates subtitles into 100+ languages through Google Translate without an API key. · github.com, 12 Oct 2026
Windows download
The README documents building a single-file Windows executable with PyInstaller; it downloads Whisper model weights on first run rather than bundling them. · github.com, 12 Oct 2026

Where asub stands on Freedom251

Look at these too