Releases Index
Wispr Flow

Wispr Flow

$npx @buildinternet/releases get wispr-flow
Recently Shipped5 releases · updated Oct 13, 2026

Recently shipped Canto, a proprietary real-time speech model now running all dictation automatically.

Canto beats the third-party stack on messy audio. Measured on 9.8 hours of real-world English recordings from 2,300+ speakers, it posted the lowest word error rate of every model tested, Google, OpenAI, AssemblyAI, and Deepgram included. It also led on stress-test audio: background conversation, music, traffic, wind, whispered speech. A 10x-scale successor is in training, targeting harder conditions and broader language coverage.

Notetaker reached Windows and pulls in outside AI tools. Windows joins Mac, with meeting detection, personal-dictionary term handling, in-call catch-up, cross-meeting search with citations, and draft generation. Gemini joined Claude and ChatGPT in one-click setup, and any MCP-compatible tool can now read transcripts — connection grants transcript access only.

Meeting capture got sturdier.

  • Speaker detection in Teams gallery view and Google Meet
  • Stuck Windows meeting uploads now finish on their own, and recordings recover from save or upload errors
  • @-mention people in meeting notes, with hover contact cards
  • A warning when the mic picks up no sound, plus a “Speaking a different language?” prompt to add languages on Mac and Windows

Privacy controls tightened. Model training stays off for Growth and Enterprise members. Turning off dictation Cloud Storage no longer stops Scratchpad from syncing across devices.

Stuck meeting uploads self-recover; Teams gallery speaker detection

This release5 featuresNew capabilities1 enhancementImprovements to existing features3 fixesBug fixesAI-tallied from the release notes

Stuck Windows meeting uploads now finish on their own and meeting recordings recover from save and upload errors. The update also adds speaker detection in Teams gallery view and Google Meet, @-mentions in meeting notes, contact cards on hover, a warning when the mic picks up no sound, a prompt to add a spoken language, and stops idle Teams windows from triggering meeting pop-ups.

Read more ↗

Model training stays off for Growth/Enterprise; note access logged

This release2 featuresNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes

Model training stays off for Growth and Enterprise plans for all members, and Enterprise admins can review note and transcript access in Audit Logs under a new Note access category. Audit Logs now also capture more membership and domain changes, including role changes, invitations, domain additions and removals, and additional join and leave paths.

Read more ↗

Scratchpad sync now independent of dictation storage

This release2 featuresNew capabilitiesAI-tallied from the release notes

Flow shows a "Speaking a different language?" card prompting you to add languages on Mac and Windows. Turning off dictation Cloud Storage no longer stops Scratchpad sync across devices.

Read more ↗

Canto speech model now powers Flow for everyone

This release1 featureNew capabilitiesAI-tallied from the release notes

Flow now runs on Canto, Wispr Flow's first proprietary speech model, rolled out to everyone automatically. On 9.8 hours of real-world English recordings from over 2,300 speakers, Canto posted the lowest word error rate of all tested models, including Google, OpenAI, AssemblyAI, and Deepgram.

Read more ↗

Notetaker lands on Windows; Gemini and MCP connections added

This release6 featuresNew capabilitiesAI-tallied from the release notes

Notetaker is now available on Windows alongside Mac, with one-click Gemini setup alongside existing Claude and ChatGPT connections, plus MCP access that grants transcripts but not dictations. The release adds meeting transcription in 21 languages, Outlook calendar support, and imports from Otter and Granola, with admin controls for access, sharing, and consent requirements.

Read more ↗

Sign-in handoff reliable; Play Store fallback for uninstalled app

This release1 enhancementImprovements to existing features1 fixBug fixesAI-tallied from the release notes
v2.3.2

Android sign-in now reliably returns you to Flow across providers and browsers. If the app isn't installed, you land on the Play Store instead of a desktop download page.

Read more ↗

Otter transcripts import into Notetaker; teams assignable at invite

This release4 featuresNew capabilities1 enhancementImprovements to existing featuresAI-tallied from the release notes
v1.6.721

Otter.ai meeting transcripts can now be imported into Notetaker, preserving speaker names and running in the background. Team owners can assign new members to a team at invite time, and org-wide or department-wide dictionary words area now shareable.

Read more ↗

Otter transcripts import to Notetaker; team invites get org dictionaries

This release3 featuresNew capabilities2 enhancementsImprovements to existing featuresAI-tallied from the release notes
v1.6.721

Otter.ai meeting transcripts can now be imported into Notetaker, preserving speaker names, with background processing. Admins can assign teams at invite time, and dictionary entries can be shared org-wide or department-wide. Updates now wait until you're idle before restarting Flow.

Read more ↗

Org-wide Notetaker toggles; self-serve Growth plans

This release2 featuresNew capabilitiesAI-tallied from the release notes
v1.6.675

Admins can now toggle Notetaker on/off org-wide from the admin portal. Teams can self-serve purchase Growth plans (dictation-only or with unlimited Notetaker) with monthly or annual billing.

Read more ↗

Org-wide Notetaker toggle; self-serve Growth plans

This release2 featuresNew capabilitiesAI-tallied from the release notes
v1.6.675

Admins can now toggle Notetaker on or off org-wide from the admin portal, with a confirmation step before disabling. New self-serve Growth plans let teams buy dictation-only or bundle in unlimited Notetaker, with monthly or annual billing, without a sales call.

Read more ↗

Google sign-in uses in-app browser; reports send in background

This release2 featuresNew capabilitiesAI-tallied from the release notes
v2.2.4

Google sign-in now uses a secure in-app browser tab that returns users straight to Flow, with a resume prompt for interrupted sign-ins. Issue reports, feedback, and transcription reports keep sending even if users leave the screen, with clear busy-state indicators.

Read more ↗

Dictation works with virtual mics; team trials added

This release8 featuresNew capabilities2 enhancementsImprovements to existing features1 fixBug fixesAI-tallied from the release notes
v1.6.580

Flow now lets you pick virtual and routing audio devices like Krisp, NVIDIA Broadcast, or BlackHole as your dictation mic, behind a "Show other devices" expander. Also adds daily teammate-joined digests for admins, a 14-day trial for new team members, and a quieter background startup on Windows.

Read more ↗

Virtual mics supported; team digests land

This release2 featuresNew capabilities5 enhancementsImprovements to existing featuresAI-tallied from the release notes
v1.6.580

Flow now supports virtual and routing audio devices like Krisp, NVIDIA Broadcast, BlackHole, and VDI redirects, accessed via Settings > Microphone. Team admins get a daily email digest of new joiners, and new members receive a 14-day trial even on paid plans.

Read more ↗

Android sign-in and reports improved

This release2 fixesBug fixesAI-tallied from the release notes
v2.2.4

Android sign-in with Google now happens in a secure in-app browser tab that returns you straight to Wispr Flow, and issue reports, feedback, and transcription reports keep sending even if you leave the screen. This addresses two significant UX pain points: sign-in flows that previously landed users on random browser tabs or the website, and reports that could get lost when navigating away.

Read more ↗

Notetaker launches for meetings; transcription with live summaries

This release8 featuresNew capabilitiesAI-tallied from the release notes

Wispr Flow Notetaker is now available on Mac, recording meetings, transcribing with speaker names from calendar invites and live re-reading, and generating topic-based summaries with action items. Ask-anything queries across meeting history, pre-meeting briefs, and MCP access for Claude, ChatGPT, and custom agents are included.

Read more ↗

Dictation History plays back original audio

This release1 featureNew capabilitiesAI-tallied from the release notes
v1.6.399

Users can now play back the original audio from dictations recorded in the last 14 days to verify audio quality and troubleshoot setup issues. Playback pauses and resumes across rows and stops automatically when switching rows, on both Mac and Windows.

Read more ↗

Notetaker launches; audio playback in History

This release2 featuresNew capabilitiesAI-tallied from the release notes
v1.6.399

Wispr Flow Notetaker records meetings, transcribes and summarizes with speakers and decisions, inclusions in existing plans. Audio playback from Dictation History lets users replay the last 14 days to flag audio issues.

Read more ↗

Rich text snippets; Pro teams get leaderboard

This release3 featuresNew capabilitiesAI-tallied from the release notes
v1.6.288

Snippets now support bold, italic, links, and lists, preserving formatting in any app. Pro teams get the leaderboard (previously Enterprise-only), and admins can invite multiple teammates at once.

Read more ↗

Snippets support rich text; Pro leaderboard ships

This release3 featuresNew capabilitiesAI-tallied from the release notes
v1.6.288

Snippets now support bold, italic, links, lists, and other rich text formatting that pastes into any app. The leaderboard is now available to Pro teams, and team admins can invite multiple teammates at once.

Read more ↗