OpenWhispr: open-source dictation, meetings and notes
Don’t want to install OpenWhispr? Drop the file here.
The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.
Dictate into any app, record meetings with speaker labels, or import files and YouTube links: OpenWhispr runs local Whisper or Parakeet, or calls a cloud model with your key.
Get OpenWhispr Official site & pricing
OpenWhispr covers dictation, meeting capture with speaker labels, and file import, using local whisper.cpp or Parakeet, or a cloud model with your key. MIT-licensed, all three desktop OSes.
If you only need a recording turned into a transcript and subtitles, a hosted service saves the model downloads and keeps the laptop free.
What it is
OpenWhispr is an MIT-licensed Electron app for macOS, Windows and Linux. A global hotkey dictates into any app; a second hotkey dictates in one language and pastes another. It detects Zoom, Teams and FaceTime calls and transcribes them with local speaker diarization, keeps searchable notes, and imports existing audio and video by drag-and-drop, batch upload or a pasted YouTube or audio URL. Models run locally (Whisper on Metal, CUDA or Vulkan; NVIDIA Parakeet via sherpa-onnx) or in the cloud with your own keys. It also exposes an API and an MCP server. The project moved from HeroTools/open-whispr to OpenWhispr/openwhispr; the latest release is v1.10.2 (15 September 2026).
Watch out for: Local quality and speed depend on your hardware; cloud modes send audio to the provider you pick. On Intel Macs live speaker identification is unavailable.
A hosted pass for the long recordings
Local transcription of a two-hour file ties up the laptop. For long recordings and back catalogues:
- Drop the audio or video file into the box at the top of this page, or paste a link (YouTube, a podcast or RSS feed, Google Drive, Twitch or Kick). Nothing to install and no GPU needed.
- The language is detected automatically and the transcript stays in the language that was spoken (WhipScribe does not translate).
- Read the summary free. A pack from $6 (500 minutes) opens the full transcript and the downloads: TXT, DOCX, SRT, VTT and JSON. Packs are one-time purchases and credits never expire.
- Files can be up to 10 hours or 5 GB per file.
Related: Transcribe large files · SRT generator · SuperWhisper · MacWhisper alternatives · Pricing
Install / use
Go to OpenWhispr github.comKey specs
What people actually do with OpenWhispr-style transcription
The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.
Features
| Speaker diarization | Yes |
| Word-level timestamps | Not stated |
| Streaming / real-time | Yes |
| Languages supported | — |
| HIPAA eligible | No |
Links
- github.com/OpenWhispr/openwhispr ↗MIT · Electron · v1.10.2 on 2026-09-15
- docs.openwhispr.com ↗platform guides, API and MCP setup
OpenWhispr vs Whipscribe
| Feature | OpenWhispr | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free (MIT); bring your own key for cloud models | $6–$24 one-time packs (credits never expire) · first 20 minutes free |
| Speaker identification | Yes | Named in the summary, key quotes and chapters |
| Word timestamps | No | Yes |
| Streaming | Yes | No |
| Languages | — | 99 |
| Platforms | macOS, Windows, Linux | Web, API, MCP |
Alternatives to OpenWhispr
Frequently asked about OpenWhispr
Is OpenWhispr free?
Yes, the app is MIT-licensed and free for personal and commercial use. Cloud transcription and AI features use the provider you connect, billed by that provider.
Can OpenWhispr transcribe existing files?
Yes. Its audio import takes dragged files, batch uploads or a pasted YouTube or audio URL, with optional speaker detection.
Does OpenWhispr work offline?
With local models, yes: Whisper (GPU-accelerated on Metal, CUDA or Vulkan) and NVIDIA Parakeet run on your machine. Cloud modes send audio to the provider you select.
Is OpenWhispr the same project as HeroTools/open-whispr?
Yes. GitHub redirects the old HeroTools/open-whispr address to OpenWhispr/openwhispr.
Does OpenWhispr identify speakers?
Yes, on-device speaker labelling with voice fingerprints for meetings, except on Intel Macs, where it is unavailable because its ONNX Runtime dependency no longer ships x86_64 macOS binaries.
What is OpenWhispr?
OpenWhispr covers dictation, meeting capture with speaker labels, and file import, using local whisper.cpp or Parakeet, or a cloud model with your key. MIT-licensed, all three desktop OSes.
Does OpenWhispr work on Mac, Windows and Linux?
OpenWhispr runs on macOS, Windows and Linux.
How do I install OpenWhispr?
Download the installer for your platform from https://github.com/OpenWhispr/openwhispr/releases/latest. No terminal needed.
Can OpenWhispr transcribe live audio?
Yes — OpenWhispr supports streaming / live input, not just finished files.
Is OpenWhispr HIPAA compliant?
OpenWhispr does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.
What are the limitations of OpenWhispr?
Local quality and speed depend on your hardware; cloud modes send audio to the provider you pick. On Intel Macs live speaker identification is unavailable.
Who is OpenWhispr best for?
People who want one open-source desktop app for dictation and meeting notes, with the choice of fully local models.
What should I know before choosing OpenWhispr?
If you only need a recording turned into a transcript and subtitles, a hosted service saves the model downloads and keeps the laptop free.
Can I use OpenWhispr in the browser?
No — OpenWhispr is a macOS, Windows and Linux application, not a web app. You install it rather than sign in to it.
Where is the OpenWhispr source code?
On GitHub at github.com/OpenWhispr/openwhispr.
Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.
Transcribe your recordings
Running OpenWhispr yourself? Send the same file here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step
Explore
All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing
Long recording to get through?
One file up to 10 hours, as an upload or a link: see transcribing a long MP3 or M4A, a podcast episode as text from its link and the SRT generator.
Comparing tools before you pay?
If you would rather pay a service than run software yourself: see how the best transcription services compare, cheap transcription services and the real cost per hour and our transcription service with prices and turnaround.