OpenWhispr
openwhispr.com
- Free plan
- Windows
- macOS
- Linux
- iPhone and iPad
What OpenWhispr is
OpenWhispr is an open-source voice-to-text assistant for dictating in apps and turning audio into transcripts and notes. Dictation works in apps that accept text, including ChatGPT, Claude, Cursor, Google Docs, Gmail, Slack, and Teams. It supports more than 100 languages with automatic language detection. Its meeting note taker captures computer audio without joining a call as a bot, then can create structured notes with decisions and action items. It works with Zoom, Google Meet, Microsoft Teams, Slack, Discord, Webex, and other apps that play computer audio, without plugins or integrations. Users can process speech locally, keeping audio on their device, or use OpenWhispr Cloud, which says it discards audio without retaining it. The company says it does not use user content to train AI models. The free plan includes 2,000 transcription words per week and five hours of meeting recordings per month. Pro costs $6.67/user/mo billed annually and adds unlimited cloud transcription, 20 hours of meeting recordings per month, device sync, personal API access, and MCP integration. Business costs $13.33/user/mo billed annually. OpenWhispr runs on iOS, Linux, macOS, and Windows.
Who it suits
It suits people who want to dictate into text-enabled apps, transcribe audio, or create meeting notes across supported platforms. Local processing may suit users who want audio kept on their device; cloud processing is another option.
Good to know, and what to watch
- Supports more than 100 languages with automatic detection.
- Local speech processing keeps audio on the device.
- Meeting notes can include decisions and action items.
- Works across iOS, Linux, macOS, and Windows.
- Free transcription is limited to 2,000 words weekly.
- Free meeting recordings are limited to five hours monthly.
- Pro costs $6.67/user/mo billed annually.
Plans
Every plan and priceEnterprise
Free
Pro
Business
Free plan
Getting started
- Open the OpenWhispr website
- Choose the Free, Pro, Business, or Enterprise plan
- Install it on iOS, Linux, macOS, or Windows
- Use local models or OpenWhispr Cloud for speech processing
- Dictate into a text-accepting app or upload a supported audio file
- Capture computer audio for meeting notes
Limits to check
The Free plan allows 2,000 transcription words per week and five hours of meeting recordings per month. Pro raises meeting recordings to 20 hours monthly, while Business provides unlimited meeting recordings; Enterprise pricing is custom.
The Club's review
OpenWhispr combines in-app dictation, audio transcription and meeting note capture in an open-source application. It is best suited to people who want one workflow across many desktop apps and meeting services, with a choice between on-device and managed cloud processing. The main buying question is whether the Free limits cover your regular recording and transcription volume.
Overview
OpenWhispr turns speech into text inside applications that accept typing, including ChatGPT, Claude, Cursor, Google Docs, Gmail, Slack and Teams. It also handles uploaded recordings and can build structured meeting notes from computer audio without joining a call as a bot. That makes it a practical single tool for writers, developers, support teams and meeting-heavy organizations, while users who need only occasional transcription may find the broader feature set unnecessary.
The software is open source under the MIT license. Local speech models keep processing on the device, which suits sensitive work and reduces dependence on a network connection. OpenWhispr Cloud processes audio through its managed API in real time and says it discards the audio without retaining it; it also says user audio, transcriptions and other content are not used to train AI models.
Key features
Dictation and transcription
Support for more than 100 languages and automatic language detection make the dictation layer useful for multilingual users. Uploads accept MP3, WAV, M4A, WebM, OGG, FLAC, AAC and formats supported by FFmpeg. A transcript editor, speaker labels, caption export and searchable library help turn recordings into reusable work rather than one-off text.
Meeting notes
The note taker captures computer audio from Zoom, Google Meet, Microsoft Teams, Slack, Discord, Webex and other applications that play audio. It needs no plugin or integration and can produce notes with decisions and action items. This bot-free approach avoids adding an automated participant, although the amount of meeting audio you can process depends heavily on the plan.
Privacy and controls
Cloud data is encrypted in transit with TLS and at rest, and diagnostic reporting is off by default. The homepage states that the service is HIPAA compliant and independently verified for AICPA SOC 2 and ISO 27001. Those claims will matter to organizations assessing regulated or confidential workflows, while local processing remains the clearest option when audio should stay on the device.
Pricing
Free
Free costs nothing and is always free. It includes 2,000 words of transcription per week, five hours of meeting recordings per month, unlimited local AI models, community support and unlimited cloud transcription when you supply your own API keys. It is a good way to evaluate dictation and local models, but the weekly word allowance and meeting cap can constrain frequent users.
Pro
Pro costs $6.67 a month, billed at $80/user billed annually. It adds unlimited cloud transcription, 20 hours of meeting recordings per month, Agent mode, device sync, personal API access, MCP integration, the iPhone and iPad app and email support. This is the sensible tier for an individual who needs regular cloud transcription and cross-device use; it still imposes a monthly meeting limit.
Business and Enterprise
Business costs $13.33 a month, billed at $160/user billed annually. It keeps unlimited cloud transcription, removes the meeting-recording limit, and adds chat over your data and priority support. It fits teams whose meeting volume makes Pro's 20-hour allowance impractical. Enterprise uses custom pricing and adds team administration, SSO, SAML, SCIM, audit logs, retention controls and dedicated support for organizations needing formal identity and governance controls.
Platforms
OpenWhispr runs on iOS, Linux, macOS and Windows. The iPhone and iPad app is included with Pro, while desktop users can use the core workflows across all four supported operating systems.
Who it's for
Choose OpenWhispr if you want dictation embedded in everyday apps, bot-free meeting capture and a local-processing option in one product. It is particularly suitable for multilingual users, privacy-conscious professionals and teams that need structured decisions and action items. It is less compelling for someone seeking only a basic transcription API or whose meeting volume exceeds Pro but does not justify Business or custom Enterprise arrangements.
Pros and cons
Pros
- Local and cloud processing: on-device models support privacy-sensitive work, while managed cloud processing offers real-time convenience.
- Broad compatibility: dictation works in common writing and collaboration apps, and meeting capture covers major services without plugins.
- Useful editing workflow: speaker labels, caption export, a transcript editor and searchable library extend beyond raw speech-to-text.
- Open-source foundation: the MIT license allows inspection and use of the software under a permissive license.
Cons
- Free usage caps: 2,000 transcription words per week and five meeting hours per month may be quickly exhausted.
- Pro meeting ceiling: 20 recording hours per month means heavier meeting users must move to Business.
- Annual billing: the advertised Pro and Business monthly rates require annual per-user billing.
- Some advanced capabilities are paid: device sync, personal API access, MCP integration and the mobile app start with Pro.
Alternatives
For a wider comparison of recording-focused tools, see Podcast Transcription Software and Meeting Recording Software.
- Simon Says suits buyers who prefer pay-as-you-go transcription and a broader mix of extension, web, mobile and self-hosted platforms.
- Happy Scribe is an alternative for users wanting a free plan with unlimited meeting recordings, capped at 45 minutes per recording.
- Whipscribe is worth considering when a first transcript of any length and 99+ language auto-detection are the priority.
- AssemblyAI is the better fit for API-oriented teams seeking usage-based Universal-2 transcription.
- Rev fits users who want an English-focused free tier with 45 AI transcription and caption minutes per month.
- AudioPod AI is aimed at broader audio creation workflows with credits for text-to-speech and music as well as uploads.
- Speechmatics is an API and self-hosted option with free credits and concurrent real-time sessions.
- Trint is a paid transcription platform with a free trial and broad web, desktop and mobile coverage.
Verdict
OpenWhispr is a strong choice for individuals and teams that want multilingual dictation, bot-free meeting notes and the option to keep speech processing local. Its open-source model and broad app compatibility strengthen the case, but Free's caps and Pro's 20-hour meeting allowance make Business the practical step-up for heavy meeting users. Look elsewhere if you need only an API, English transcription, or a non-annual pricing structure.
The verdict
OpenWhispr offers dictation, transcription, and meeting notes, with local and cloud processing options. Its free plan has weekly and monthly usage limits; Pro is listed at $6.67/user/mo billed annually.
Questions people ask
Is OpenWhispr free?
Yes. The Free plan costs nothing and is always free. Paid plans start at $6.67/user/mo billed annually.
Which platforms does it support?
OpenWhispr runs on iOS, Linux, macOS, and Windows.
Does it process audio locally?
Yes. Local speech models process audio on the user's device. OpenWhispr Cloud processes audio through its managed API and says it discards the audio without retaining it.
Does OpenWhispr use content for AI training?
The company says it does not use users' audio, transcriptions, or other user content to train AI models.
What does Pro add?
Pro includes unlimited cloud transcription, 20 meeting-recording hours per month, agent mode, device sync, personal API access, MCP integration, the iPhone and iPad app, and email support.
Is OpenWhispr open source?
Yes. OpenWhispr says its software is open source under the MIT license.
What the maker publishes
- AI training
- OpenWhispr says it does not use users' audio, transcriptions, or other user content to train AI models. source
- App compatibility
- Dictation works in apps that accept text, including ChatGPT, Claude, Cursor, Google Docs, Gmail, Slack, and Teams. source
- Audio formats
- Audio upload supports MP3, WAV, M4A, WebM, OGG, FLAC, AAC, and formats supported by FFmpeg. source
- Cloud processing
- OpenWhispr Cloud processes audio through its managed API in real time and says it discards the audio without retaining it. source
- Company location
- The site footer identifies Gizmo Labs Inc. and gives its address as 221 W 9th Street, Wilmington, Delaware 19801, USA. source
- Compliance
- The homepage states that OpenWhispr is HIPAA compliant and independently verified for AICPA SOC 2 and ISO 27001. source
- Headquarters
- Wilmington, Delaware, USA source
- Integrations
- The Pro plan includes personal API access and MCP integration in apps. source
- Languages
- The product supports 100+ languages with automatic language detection. source
- Local processing
- With local speech models, audio is processed on the user's device and is not transmitted elsewhere. source
- Meeting app support
- The meeting note taker works with Zoom, Google Meet, Microsoft Teams, Slack, Discord, Webex, and other apps that play computer audio, without plugins or integrations. source
- Meeting notes
- Its meeting note taker captures computer audio without joining calls as a bot and can create structured notes with decisions and action items. source
- Open-source license
- OpenWhispr says its software is open source under the MIT license. source
- Purpose
- OpenWhispr is an open-source voice-to-text assistant for dictating in apps and turning audio into transcripts and notes. source
- Security controls
- The security page says cloud data is encrypted in transit using TLS and at rest, and diagnostic reporting is off by default. source
- Support
- The Free plan includes community support, Pro includes email support, Business includes priority support, and Enterprise includes dedicated support. source
Checked against the maker's pages on 30 Sept 2026.