VoiceThe open-source alternative to Wispr Flow + Granola

Hold a key, talk and the clean text lands where you were typing. Record a call from your browser, jot a few lines and AI writes the notes with the transcript, in the same suite as your CRM, Docs and Track.

fig. 0 · the waveform of a voice

What Voice does.Dictation and meetings in one app.

  • Dictation anywhere

    Hold Alt+Space in any zerosoft text field, or double tap it for hands-free. A desktop app to dictate into any program is on the way.

  • AI cleanup

    Filler words go, punctuation and lists appear and spoken corrections like "Monday, no, Tuesday" are applied, with your dictionary, snippets and a tone per context.

  • Meeting notes with no bot

    Record your microphone, or your microphone and a browser tab with Meet, Zoom or Teams. No extra participant joins the call and the audio is discarded once transcribed.

  • Transcript, summary and tasks

    A live transcript split into Me and Them, AI notes built from what you jotted with a template per meeting type, plus decisions and next steps.

  • Connected to the suite

    Next steps become Track issues or CRM tasks, the note goes to Docs or Notes and, linked to a Cal booking, lands on the contact timeline. Ask any meeting what was said.

  • The AI you choose

    Transcription goes through the provider you configure (Whisper through the AI Gateway, OpenAI, Deepgram or AssemblyAI), with the same quota and usage log as the other apps.

Voice outside the browser.With the desktop app.

With the desktop app, Voice dictation works in any app on your computer, not just in zerosoft.

  • One shortcut, any app

    Option + Space on Mac, Ctrl + Alt + Space on Windows. It uses the language, dictionary and styles you set up in Voice.

  • Meetings with the window behind

    While a meeting records, a small indicator on top of everything shows the time and lets you open or stop it.

No Linux build yet. On your phone, add zerosoft to your home screen from the browser.

The app’s dictation bar, redrawn: it shows up at the bottom center, over whatever app is in front.

Voice next to Wispr Flow + Granola.Our count, capability by capability.

parity with Wispr Flow + Granola

73%of what Wispr Flow + Granola does, by our count

Included
26
Partial
17
Missing
5

We measured 48 Wispr Flow + Granola capabilities: each one we have scores 1, a partial one 0.5 and a missing one 0, with double weight for the core ones; this is our own assessment, checked against the code on November 17, 2026. See the changelog

  • Dictation in any app57%
  • AI cleanup and formatting87%
  • Dictionary, snippets and styles66%
  • Voice commands and rewriting100%
  • Desktop, mobile and usage50%
  • Meeting capture77%
  • AI notes and summaries87%
  • Chat with meetings75%
  • Organize and share87%
  • Integrations and API80%
  • Teams, privacy and admin62%
Everything Voice includes43

[x] Included[+] Better[~] Partial

Voice capabilities compared with Wispr Flow + Granola
CapabilityVoiceWispr Flow + Granola
Dictation in any app
Dictate into any text field with a shortcut PartialHold Alt+Space (or the field button) in any zerosoft field and the clean text is inserted at the cursor. In any other app, the native desktop app (Tauri, Mac and Windows): hold Option + Space on Mac or Ctrl + Alt + Space on Windows (configurable), or tap it to start and stop, and the text is pasted where the cursor is, with the clipboard put back afterwards. A small HUD shows the level and a timer. Shortcuts made only of modifiers (Fn, Control + Option) are not available. Tested with the parts in Rust unit tests; the real paste into other apps and real microphone audio are checked by hand, not automaticallyWispr Flow + Granola: Yes
Hands-free mode IncludedDouble tap the shortcut, or click the field button, and Voice listens until you tap again. In the desktop app, a quick tap of the shortcut keeps listening until the next tap, in any app; Esc cancelsWispr Flow + Granola: Yes
More than 100 languages Partial16 languages to pick in settings, plus automatic detection with whatever the configured provider supports (Whisper, Deepgram or AssemblyAI)Wispr Flow + Granola: Yes
Paste or copy the last dictation IncludedCtrl+Cmd+V (Mac) or Ctrl+Alt+Shift+V pastes the last dictation from the server history, also the ones made in the desktop app; every dictation can be copied again from the historyWispr Flow + Granola: Yes
AI cleanup and formatting
Remove filler words and fix grammar and punctuation IncludedAI cleanup of fillers, punctuation and capitals, with a rules fallback when AI is offWispr Flow + Granola: Yes
Apply spoken self-corrections PartialSpoken corrections ("Monday, no, I mean Tuesday", "scratch that") are applied by the AI prompt and by a rules fallback; the rules cover clear cases only and the AI behaviour has not been measured against real recordings yetWispr Flow + Granola: Yes
Spoken lists and punctuation Included"A list: eggs, milk and bread" becomes a bulleted list, "first… second…" or "number one… number two…" a numbered one. Spoken punctuation ("colon", "comma", "open paren", "open quote", "new paragraph") turns into the symbol, in English, Spanish and Portuguese. An email gets its greeting and sign-off on their own lines; a chat stays as saidWispr Flow + Granola: Yes
Dictionary, snippets and styles
Personal dictionary IncludedWords to spell right (they also bias the transcription) and replacements; fixing a dictation in the history adds the corrected names and terms by itself, with undo. Fixes made in other apps after pasting are not seenWispr Flow + Granola: Yes
Voice snippets IncludedWispr Flow: a spoken cue inserts saved text, like a booking link or a frequent answerWispr Flow + Granola: Yes
Tone by app IncludedFormal, neutral or casual tone per context (email, chat, note, other), picked from the app and the field. A cleanup mode on top: raw (as spoken), clean, formal everywhere or by app, the same on the web and in the desktop appWispr Flow + Granola: Yes
Voice commands and rewriting
Edit selected text by voice IncludedTurn on Command Mode, select text in any zerosoft field, hold the shortcut and say "make it shorter" or "translate it": the selection is replaced. Off by default. Other apps need the desktop appWispr Flow + Granola: Yes
Saved rewrite prompts IncludedBuilt-in and saved rewrites (your own or shared with the workspace): select text and pick one from the pencil next to the dictate button, or say its name in Command ModeWispr Flow + Granola: Yes
Desktop, mobile and usage
Mac and Windows desktop apps PartialA native app for Mac and Windows built with Tauri (source in desktop/): the system webview instead of a bundled Chromium, dictation in any app done in Rust (global shortcut, microphone, HUD, paste), a guided first run for the microphone and Accessibility, settings with language, cleanup, dictionary and history (the same ones as Voice on the web), menu bar menu, native notifications and signed updates. Not signed by Apple yet. Meeting notes with system audio are not in this versionWispr Flow + Granola: Yes
Keep dictations without a connection PartialIn the desktop app, a dictation that cannot reach the server stays on the computer and is sent again from the menu bar or the history. Transcription still needs the server: there is no on-device modelWispr Flow + Granola: Yes
Sync across devices PartialDictionary, styles and history live on the server, so every browser and the desktop app (with your session) use the same ones. No phone app yetWispr Flow + Granola: Yes
Usage stats IncludedWords this week, dictations, minutes and the apps where you dictate most, plus an Analytics page with meetings, words per minute, activity per day and by hour against the previous period; admins see a team panel per person (numbers only, never the text)Wispr Flow + Granola: Yes
Meeting capture
Record meetings without a bot PartialNo bot: the browser asks to share a tab or the screen with its audio (Meet, Zoom or Teams on the web, or a native call app with the system audio where the browser offers it) and records it next to your mic; the meeting audio is asked by default. The Mac desktop app records the system audio natively with ScreenCaptureKit (macOS 13 or later, Screen & System Audio Recording permission). Tested with fake capture only, not yet with a real call; Windows desktop still goes through the browser shareWispr Flow + Granola: Yes
Starts listening when the meeting opens IncludedNew meeting, Take notes on a calendar event or ⌘K open the meeting already recording the microphone (in the desktop app, also the system audio when allowed). Tab audio in the browser needs one more click because the browser asks to pick the tab. A blocked or missing microphone is shown with a retry, and a link never turns the microphone onWispr Flow + Granola: Yes
Live transcript IncludedSearchable transcript split into Me (mic) and Them (tab), arriving in parts of about 20 secondsWispr Flow + Granola: Yes
Calendar sync and meeting reminders IncludedThe Cal bookings you host or co-host plus the Google Calendar and Outlook events connected in Cal, with attendees and the call link; take notes from an event and get a reminder a few minutes before (in the page and as a browser notification) while zerosoft is open in a tab. Admins only see their own meetings, not the whole workspaceWispr Flow + Granola: Yes
Speaker names PartialMe and Them by audio source, separate speakers with Deepgram or AssemblyAI, and names set by hand; no names from the callWispr Flow + Granola: Yes
In-person meetings and phone calls PartialMicrophone mode records in-person meetings from the browser; no phone calls and no mobile appWispr Flow + Granola: Yes
AI notes and summaries
AI notes from your notes and the transcript IncludedAI combines your notes with the transcript and the template in headings and nested bullets; your own lines stay in ink and the AI ones in gray. The note is edited in place like a document (Enter adds a bullet, Tab nests it) and saves itselfWispr Flow + Granola: Yes
Note templates IncludedSales, 1:1, stand-up, interview, customer and general, plus your ownWispr Flow + Granola: Yes
See where each point came from IncludedEach point says whether it came from your notes or from the transcriptWispr Flow + Granola: Yes
Pre-meeting brief IncludedBefore a meeting, AI sums up what you discussed with the same attendees and what is still open, only from your own meetings, with links to eachWispr Flow + Granola: Yes
Follow-up email PartialAI drafts the follow-up from the notes, addressed to the attendees, right from the bar under the notes; you edit it and send it from your connected Gmail or Outlook, copy it, or open it in Gmail or Outlook. Sending was checked end to end with a test Outlook mailbox onlyWispr Flow + Granola: Yes
Calendar event and attendees on the note PartialThe date chip on a note picks today's event from the connected calendar (the one happening now is chosen on its own for a new note), adds attendees from the workspace or the CRM, and groups them by company. Checked with a test Google Calendar onlyWispr Flow + Granola: Yes
Chat with meetings
Chat with one meeting IncludedAn "Ask anything" bar under the notes (⌘J or /) opens the chat during and after the meeting: recipes first, answers that stream in and cite the transcript time, "Say more", separate chats with their history, a fast or thorough model, a text file attached to the question and the question dictated by voice. Checked end to end with a test model; the quality of citations with real models is not measured yetWispr Flow + Granola: Yes
Chat across meetings PartialQuestions across your meetings and the ones teammates shared with you (only what each share lets you see), with follow-ups, dates like "last week" and names of attendees. Answers stream in and link to each meeting and moment. Meetings are picked by words, names and dates, up to six of yours and three shared; there is no semantic search, so a question worded differently from what was said can miss a meetingWispr Flow + Granola: Yes
Saved prompts (recipes) IncludedBuilt-in recipes (follow-up email, my todos, longer notes, TL;DR and more) and your own, run with / or from the recipe library in the meeting, on one meeting or across meetings. Create and edit them there and share them with the workspace (not by a public link)Wispr Flow + Granola: Yes
People and companies from meetings PartialA meeting links to a CRM contact (by hand or from the Cal guest email); no automatic directory of people and companiesWispr Flow + Granola: Yes
Organize and share
Share notes by link IncludedA read-only link with access for the workspace, for the people you pick or for anyone; the transcript only if you include it; change or revoke it anytime. No collaborator role yetWispr Flow + Granola: Yes
Spaces and folders PartialYour own folders with one level of subfolders and a "Shared with me" view with what the team shared; no custom spaces with their own membersWispr Flow + Granola: Yes
Copy as Markdown and send by email IncludedCopy as Markdown, send to Docs or Notes, and send the follow-up email from your Gmail or Outlook or open it thereWispr Flow + Granola: Yes
Integrations and API
Send notes to Slack and Notion IncludedPost the notes to a public Slack channel with the workspace Slack app (installed from Track). Admins also create a Notion page under the page they pick, with a Notion credential saved in Flow; members copy the Markdown insteadWispr Flow + Granola: Yes
Send notes to the CRM IncludedThe notes land on the zerosoft CRM contact timeline and next steps become CRM tasksWispr Flow + Granola: Yes
Zapier PartialNo Zapier app; the voice.meeting.completed and voice.notes.ready webhooks work with Zapier "Catch Hook", and Flow covers the same automationsWispr Flow + Granola: Yes
MCP server for AI assistants IncludedMCP server at /api/v1/voice/mcp with a voice:read key: list and read your meetings (notes and transcript), ask across them and list dictations. It only sees the key owner’s meetingsWispr Flow + Granola: Yes
API and webhooks PartialAPI v1 with voice:read and voice:write (dictate, sessions, audio chunks, dictionary). The voice.meeting.completed and voice.notes.ready webhooks only reach webhooks created by the person who recorded; creating webhooks is for admins, so a member’s meetings do not reach any webhook yetWispr Flow + Granola: Yes
Teams, privacy and admin
Team dictionary and snippets IncludedAdmins add words, replacements and snippets for the whole workspace; everyone uses them next to their ownWispr Flow + Granola: Yes
Recording notice for attendees PartialThe recorder reminds you to tell attendees; nothing is posted in the callWispr Flow + Granola: Yes
Retention and auto-deletion IncludedThe audio is never stored. Meeting transcripts and the raw transcription of dictations are deleted automatically after the days each person picks, with a maximum the admin can set for the workspace; meeting notes and the final text of each dictation stayWispr Flow + Granola: Yes
Still missing (5)

Wispr Flow + Granola has these and we don't yet. If you need one, vote for it on the public board.

  • Whisper modeWispr Flow: dictate at low volume in shared spacesVote on the board
  • Spell names from screen contextVote on the board
  • Dictation for code editorsWispr Flow: knows visible variable and function names in Cursor, Windsurf and VS Code, and @-tags files in Cursor and Windsurf chatVote on the board
  • iOS and AndroidWispr Flow keyboard on iPhone and Android; Granola apps for iOS, Android and Apple WatchVote on the board
  • SSO and SCIMWispr Flow Growth (SSO) and Enterprise (SCIM); Granola EnterpriseVote on the board

How it works.

  1. Dictate with a shortcut

    Hold a key, talk and see clean text where you were typing.

  2. Record the meeting

    Voice listens to your mic and the call tab and transcribes as you talk, split into Me and Them. With Deepgram or AssemblyAI it also tells speakers apart.

  3. Use the note

    The summary, decisions and next steps go to Docs, Notes, Track or the CRM.

Wispr Flow + Granola at list price.Against $0 on your server.

Today you pay

Wispr Flow + Granola
$26 / user / month
Team of 10
$3,120 / year

Wispr Flow Pro costs $12 per user per month billed yearly ($15 monthly) and Granola Business costs $14 per user per month. Together that is $26: a team of ten pays $3,120 a year. List prices checked on October 25, 2026. Voice on your server costs $0 plus whatever your transcription provider charges.

With zerosoft

$0
Voice on your server
$0
Team of 10 / year
$0
License
AGPLv3

Voice, inside.

zerosoft.ai/app/voice
Weekly sales review4 speakers
Summary

October closed above target; two large accounts still need follow-ups.

Decisions
  • Move Globex to negotiation
  • Review the yearly plan price in November
Tasks
  • Ana: send the proposal to Globex
  • Lucía: update the forecast in the CRM
Ask this meeting something

fig. 1 · voice, interactive viewTry Voice

Price = cost × 3.Both numbers in plain sight.

On your server, zerosoft costs $0. On zerosoft Cloud every workspace gets a free monthly plan, and above it we charge usage at three times what it costs us to serve.

  1. $0

    Self-host it

    / month, on your server

    The core is AGPLv3, with every core feature. Run it on your server and change it however you like. There is no trial and no license key.

  2. Free

    zerosoft Cloud

    / to start · then usage-based

    We run it: login, backups, updates and uptime. Every workspace starts on a free plan, then pays for usage: clicks, bookings, emails and storage. Seats are not billed, and AI is billed by tokens.

  3. Let's talk

    Enterprise

    / commercial license + support

    A commercial license with direct support from the team, on your servers or in our cloud. SSO/SAML, audit logs, custom roles and white-label are in development.

Usage on zerosoft Cloud

What is charged above the plan, per workspace per month. First what it costs us, then what you pay.

zerosoft Cloud usage above the plan, per workspace per month
ResourceIncluded per monthCharged perOur costYour price (× 3)
Link clicks25,000 clicks100,000 clicks$0.83$2.50
Bookings50 bookings1,000 bookings$4.00$12.00
Emails sent150 emails1,000 emails$1.00$3.00
Storage0.5 GB1 GB per month$0.17$0.50
  • Seats are not charged: adding people to the team does not change the bill.
  • AI is billed per token, at the provider's price × 1.2.
  • A paid workspace has a $5 monthly minimum, credited to usage.
  • Infrastructure costs measured on October 12, 2026 and rounded to the cent.

Voice questions.Migration, limits and API.

Can I use Voice today?

Yes, on the web: dictation in every zerosoft field and meeting notes at /app/voice. The workspace needs a transcription provider configured (the AI Gateway, OpenAI, Deepgram or AssemblyAI).

Is there a desktop app?

There is no published version yet. The code is in the repository: dictation into any program and system audio for meetings, on Mac and Windows. The download appears at /download with the first version, unsigned at the start.

Where is the audio processed?

By the transcription provider your workspace uses. A live recording goes in 20-second parts that are transcribed and discarded; an imported file is deleted from storage once it is transcribed, or after 24 hours if it never was. If you self-host zerosoft, you pick the provider and the key.

Does it add a bot to my meetings?

No. It records from your browser, the way Granola records from your computer, with no extra participant on the call. Let people know you are transcribing.

What is missing compared to Wispr Flow + Granola?

iPhone and Android apps, signed downloads of the desktop app, whisper mode, dictation that recognizes code and names on screen, and SSO with SCIM. The parity table above lists every capability we measure.

Stop typing.
Talk, and keep the notes.

Hold Alt+Space in any field, or start a meeting and let Voice write it up.