Price terms as published
Each line is the vendor’s own wording, split from the price capture checked on 2026-09-21. Nothing here is rounded, converted or re-worded — the full sentences stay in the review below. Lines that carry only a price continue the plan named on the line above, in the vendor’s own order.
| # | Plan / term | Checked |
|---|---|---|
| 1 | Free local dictation | 2026-09-21 |
| 2 | cloud plans from $6.67/user/month (annual) | 2026-09-21 |
One-liner: OpenWhispr is an open-source dictation and transcription application for macOS, Windows and Linux that runs local speech models (Nvidia Parakeet and Whisper-family engines) for free, with optional cloud transcription and meeting-note features on paid plans.
Verified facts (checked 2026-09-21)
| Attribute | Value | Source |
|---|---|---|
| GitHub stars | 8,415 | OpenWhispr/openwhispr via GitHub API |
| Forks | 1,034 | GitHub API |
| License | MIT | GitHub license metadata |
| Created | 2025-06-19 | GitHub API |
| Last push | 2026-09-21 (same day) | GitHub API |
| Latest release | v0.14.3 (2026-09-19) | Releases API |
| Platforms | macOS, Windows, Linux; iOS on paid plans | README + pricing page |
| Local models | Nvidia Parakeet TDT 0.6B v2; Whisper-family engines | README + model docs |
Pricing as published (annual billing, checked 2026-09-21)
| Plan | Price | Key limits |
|---|---|---|
| Free | $0 | Unlimited local models; 2,000 words/week OpenWhispr Cloud; 5 hours meeting recordings/month |
| Pro | $6.67/user/month ($80/user/year) | Unlimited cloud transcription; 20 meeting hours/month; sync, mobile app, API & MCP, agent mode |
| Business | $13.33/user/month ($160/user/year) | Unlimited meeting recordings; chat over your data; priority support |
| Enterprise | Custom | SSO/SAML/SCIM, audit logs, retention controls, dedicated support |
Bring-your-own-key cloud transcription is included on every plan, and the pricing page states zero data retention.
What it does beyond dictation
Four documented workflows: voice-to-text into any application, private AI meeting notes, a chat interface that knows your meetings, and local audio-file transcription. The use-case pages specifically address medical and legal dictation — the local-model path exists precisely because clinicians and lawyers often cannot send speech to third-party clouds.
On paid plans the developer surface is unusually broad: personal API access, an MCP server so agents can call transcription, a CLI with remote access, and an “agent mode.”
What to check before assuming it fits
- The free tier’s cloud quota is modest (2,000 words/week); everything unlimited on Free runs on your hardware.
- Meeting recordings cap at 5 hours/month free and 20 on Pro; only Business is unlimited.
- Device sync and the iPhone/iPad companion start at Pro — free is desktop-only.
- Local transcription quality and speed still depend on the model and machine you run; the project lists supported engines rather than promising one uniform experience.
Who it’s for
Anyone who wants system-wide dictation without a subscription — especially professionals with privacy constraints — and teams willing to pay roughly $7–13 per seat per month for cloud transcription, meeting workflows and MCP/API access. If you only need occasional transcription of files with no desktop integration, a standalone tool is lighter.
Repository stats, license, pricing and feature details verified against primary sources on 2026-09-21. This entry follows our verification policy. This page is a draft pending editorial review.