Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

Whisparr review

Free#73 of 99 in AI Video Caption Generators

A self-hosted Whisper CLI for batch transcription and SRT or WebVTT subtitles.

3.0/10Editor score
Whisparr3.0 Visit Whisparr

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Whisparr is an open-source, self-hosted tool that generates subtitles for audio and video files, aimed at technical users who are comfortable with a Python command-line interface. It uses OpenAI Whisper for speech transcription, handles individual files or directories, and can detect the source language automatically or accept a specified language. Its core output is SRT or WebVTT, making it a focused option for people who need subtitle files rather than a broader caption-editing workspace.

Batch processing and model selection are practical strengths for repeated jobs. Users can choose Whisper model sizes from tiny to large, and optional CUDA acceleration is available. Configuration uses JSON, with command-line overrides. This combination offers control over how transcription runs, but it also means Whisparr is better suited to people prepared to work in a terminal than to casual users seeking a graphical editor or guided workflow. The project is self-hosted and supports Windows, macOS, and Linux.

Whisparr can translate subtitles through OpenAI or Anthropic models, using provider API keys. That extends its role beyond transcription, though the translation path depends on external model providers. There is no paid-plan structure to weigh; the software is open source. Its scope remains subtitle generation: speaker diarization is described as a future enhancement, and styling or burned-in caption output is not established here. Choose Whisparr for configurable, batch subtitle generation on a supported desktop platform; look elsewhere if you need a visual editing workflow, speaker separation, or burned-in captions.

Whisparr pros and cons

  • Where it wins
    • Transcribes with selectable Whisper models from tiny to large
    • Processes directories and exports SRT and WebVTT subtitles
    • Can translate subtitles through OpenAI or Anthropic models
  • Where it doesn't
    • Requires a Python command-line workflow
    • Self-hosted desktop availability is limited to Windows, macOS, and Linux
    • Speaker diarization is a future enhancement, not a current feature

Whisparr fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update