whereismyai
Whishper
Whishper is an open-source audio transcription and subtitling suite that runs locally with a web UI.
Whishper is an open-source audio transcription and subtitling suite that operates completely locally on your machine. It features a full-featured web interface to transcribe audio and video files or media from URLs supported by yt-dlp. Users can download transcriptions in formats such as TXT, JSON, VTT, and SRT, or translate them using Libretranslate. The application includes a subtitle editor with media-synced transcription highlighting, characters per second warnings, and segment tools. Powered by FasterWhisper and MongoDB, it supports both CPU and NVIDIA GPU execution.
Whishper at a glance
- Best for: Writer, Social media creator
- Runs on: Web, self-hosted, open source
- Pricing: Free
- Released: August 2023
- Category: AI audio tool
- Website: github.com/pluja/whishper
Key features
- Transcribe audio and video files
- Transcribe media directly from URLs
- Download transcripts in TXT, JSON, VTT, or SRT
- Translate text using Libretranslate
- Edit subtitles with a built-in web UI editor
- Run 100% locally on CPU or NVIDIA GPU
- Highlight transcription based on media position
Use it for
- Transcribing audio and video files to text
- Translating transcriptions into other languages
- Editing and formatting subtitles
- Exporting transcripts to multiple file formats
Companions
Tools that articles about Whishper recommend using with it, each with its job.
- Claude Code — Plugin pings you when Claude Code needs input so you can answer by voice.
- Cursor — The original vibe-coding setup: talking to Cursor's Composer.
- Codex — Same hands-free plugin loop for Codex.
- OpenCode — Plugin support for OpenCode sessions.
- Ollama — Local model to query your on-device transcript history.
Alternatives to Whishper
- Superwhisper — Transcribes speech offline and online with custom AI modes and templates.
- OpenWhispr — Run local speech-to-text models or use cloud processing with complete data privacy.
- OpenSuperWhisper — Provides real-time transcription using customizable keyboard shortcuts and multiple engines.
- Tuxwhisper — Runs locally without cloud processing and types directly into any application.
- Wispr Flow — It transcribes natural speech into clean, formatted text 4x faster than typing.
- Scriberr — Transcribes audio locally with AI models while keeping your data private.
- AudioEnhancerMAX — Local-first audio production with verified release evidence and built-in governance.
- VocaScript — Transcribes audio and video directly in your browser with speaker detection.
- talkflow — Transcribes speech entirely on your device with no word limits or cloud accounts
- Scriber Pro 2.0 — Transcribes 4.5 hours of audio in 3.5 minutes completely offline.
- OpenLess — Keeps data local and allows the use of your own preferred ASR and LLM providers.
- GPT-SoVITS — It allows high-fidelity voice cloning with as little as one minute of data.
All Whishper alternatives