Is Speechify — Text to Speech safe?
Speechify is low risk. After Meeting Capture stops, offscreen script filters transcript lines, formats them with speaker labels, and posts them to Speechify AI summarization. Verified fields: model, transcripts, transcriptContent, stream. Testing stopped early.…
Who publishes itSpeechify Inc - no other listings under this identity, 2 shared hostnames
Speechify Inc - no other listings under this identity, 2 shared hostnames
Shared hosts - 2 hostnames
Hostnames hardcoded in this extension that few other listings call. That can mean one operator behind both, and it can equally mean a small shared vendor, so it is context rather than a conclusion. Hosts that many listings call are left out: they are services, not connections.
Speechify findings
Meeting transcripts sent for AI summaries
After Meeting Capture stops, offscreen script filters transcript lines, formats them with speaker labels, and posts them to Speechify AI summarization.
Verified fields: model, transcripts, transcriptContent, stream.
Testing stopped early.
What actually happens
You stop a Meeting Capture session that has final transcript lines.
The extension sends the full final transcript and speaker-labeled transcript text to Speechify AI summarization.
Fields sent to the summarization endpoint
- AI modelgpt-4.1-mini
The request names the model the backend should use for the meeting summary.
- Transcript objects{source: "tab", speakerName: "Other Speaker", text: "Let us review the launch plan."}
Each final transcript entry can include speaker names, whether the source was tab or microphone audio, timestamps, and the spoken text.
- Full transcript text[Other Speaker]: Let us review the launch plan.
The request also includes a single combined transcript, making the whole recorded meeting available for summarization.
- Streaming flagstream: true
The endpoint is asked to stream the generated summary back as chunks.
Captured request
Streaming response body parsed into meeting-summary chunks.
- Content-Type
- application/json
- Authorization
- Bearer <redacted>
- X-Speechify-Client
- DesktopExtension
The code that does this
Transcript formatting and AI-summary POST
Stop path forwards captured transcripts
offscreen/src/main.jsif (this.callbacks.onSummarizationRequest) { this.callbacks.onSummarizationRequest({ transcripts: this.transcripts, startTime: this.startTime, endTime: new Date().getTime() }); this.startTime = null;}TranscriptContent is built from final transcript lines
offscreen/src/main.jsoA = transcripts => { let finalRows = transcripts.filter(row => row.text.trim().length > 0 && row.isFinal); return finalRows.length === 0 ? "" : finalRows.map(row => `[${row.speakerName || (row.source === "tab" ? "Other Speaker" : "User")}]: ${row.text}`).join("\n\n");};Summarization POST includes transcript objects and combined transcript text
offscreen/src/main.jslet response = await fetch(`${ke.voiceTyping.url}/ai-scribe-summarize`, { method: "POST", body: JSON.stringify({ model: "gpt-4.1-mini", transcripts, transcriptContent, stream: true }), headers: { Authorization: `Bearer ${token}`, "Content-Type": "application/json", "X-Speechify-Client": "DesktopExtension" }, signal: abortController.signal});Remote service used for meeting summaries
- ce-voice-typing.speechify.com
Speechify AI summarization endpoint that receives full meeting transcript content.
Meeting transcripts can be emailed through Speechify
Using Meeting Capture email sharing, the sidepanel collects recipient emails, sent to an offscreen route that posts the meeting name, summary, transcript, sender, and share link to Speechify per recipient.
Testing didn't reach this step.
What actually happens
You choose the meeting email-share feature and enter recipient email addresses.
The extension posts the meeting name, generated summary, full formatted transcript, sender name, and optional share link through Speechify app backend.
Fields in each email-share request
- Recipient emailmanager@example.com
The address you enter determines who receives the meeting email.
- Sender nameAlex Reader
The request can include the display name or email from the signed-in Speechify account.
- Meeting nameWeekly roadmap sync
The email identifies the captured meeting by its tab title.
- Generated summaryThe team reviewed launch dates and assigned follow-up work.
The generated meeting summary is included in the email request.
- Formatted transcript[{type:"left",content:"Let us review the roadmap."},{type:"right",content:"I can take the follow-up."}]
The full transcript is converted into left and right entries and included with the email request.
- Share linkhttps://app.speechify.com/item/meeting-note-123?folder=abc
If a saved library item exists, the request can include a share URL for that item.
Captured request
One POST is made for each recipient; failures are collected from rejected promises.
- Content-Type
- application/json
- Authorization
- Bearer <redacted>
The code that does this
Email-share UI route and backend POST
Sidepanel validates recipients and calls send-email
sidepanel/chunk-34T6TALS.jsconst send = async () => { onChangeSendingEmail(true); onClose(); let result = await hc("meeting-capture/send-email", { to: recipients }); if (result?.result?.success) { setEmailRecipientsCount(recipients.length); setShowEmailSentToast(true); } onChangeSendingEmail(false);};Offscreen builds the email body and posts to Speechify app backend
offscreen/src/main.jslet failures = (await Promise.allSettled(recipients.map(to => fetch(`${ke.app.url}/api/meeting/email`, { method: "POST", headers: { Authorization: `Bearer ${token}`, "Content-Type": "application/json" }, body: JSON.stringify({ to, senderName, meetingName, summary, transcripts, ...(shareUrl ? { shareUrl } : {}) })})))).filter(result => result.status === "rejected");Remote service used for email sharing
- app.speechify.com
Speechify app endpoint that receives meeting email-share requests.
Meeting Capture streams Google Meet audio
Starting Meeting Capture on Google Meet requests tab-capture, opens an offscreen recorder and transcription sockets for meeting/mic audio.
Stopping saves transcripts, sends audio to Speechify, plus a summary.
No live session was tested.
What actually happens
You start Meeting Capture while a Google Meet tab is active.
The feature is gated by account state, a Meet URL, and microphone permission.
The extension captures tab and microphone audio, sends audio to Speechify transcription WebSockets, and saves the transcript and summary to Speechify library storage.
Meeting data assembled by the capture flow
- Meeting tab audioOther Speaker: Let us review the Q3 roadmap.
This can include what other participants say in the Google Meet tab you are recording.
- Your microphone audioUser: I can take the follow-up action items.
This can include what you say into the meeting while the recorder is active.
- Speaker labelsOther Speaker
Labels separate your speech from meeting-tab speech, which can identify who said each transcript line.
- Saved transcript and summarySummary: The team reviewed launch dates and assigned follow-up work.
The saved meeting note contains final transcript lines and the generated summary.
- Meeting sourcehttps://meet.google.com
The saved library item records that the content came from Google Meet.
- Meeting timing2026-07-12T20:00:39Z
Start and end times place the captured conversation in a specific time window.
Captured request
WebSocket used by separate tab-audio and microphone transcription clients.
- Authorization
- Bearer <redacted>
Captured request
Stores the meeting note after capture stops.
- Content-Type
- application/json
- Authorization
- Bearer <redacted>
The code that does this
Meeting Capture tab stream, transcription WebSockets, and library save
Background obtains the Chrome tab stream ID
background/main.jsBno = async tabId => new Promise((resolve, reject) => { chrome.tabCapture.getMediaStreamId({ targetTabId: tabId }, streamId => { chrome.runtime.lastError ? reject(new Error(chrome.runtime.lastError.message)) : streamId ? resolve(streamId) : reject(new Error("Failed to get stream ID")); });});Background sends the stream ID to the offscreen recorder
background/main.jslet response = await chrome.runtime.sendMessage({ target: "offscreen", data: { type: "meeting-capture/start", streamId, tabId, tabTitle, microphoneId, isMuted }});Offscreen connects a Speechify transcription WebSocket
offscreen/src/main.jsthis.websocket = createWebSocketClient({ onConnect: () => { this.isConnected = true; }, onMessage: message => { this.messageHandler.handleMessage(message); }, onError: error => { console.error(`[${this.options.source.toUpperCase()}] WebSocket error:`, error); }}, { url: `${ke.voiceTyping.url}/ws`, participantLabels: this.participantLabels});await this.websocket.connect();Offscreen stores the finished transcript and summary
offscreen/src/main.jslet body = { title, sourceURL: "https://meet.google.com", isPDF: false, serializedHtml: buildMeetingHtml({ title, transcripts, summary, startTime, endTime }), coverImageUrl: null, parentFolderId: folderId, analyticsProperties: { isMeetingNote: "true" }};let savedId = (await sendLibraryMessage("/library/save", body))?.body;Remote services used by Meeting Capture
- ce-voice-typing.speechify.com
Speechify transcription WebSocket endpoint used for tab and microphone audio.
- library.api.speechify.com
Speechify library endpoint used to save the meeting transcript and generated summary.
+1 more finding not shown
What Speechify can do
Permissions this extension asks for, as declared in version 14.11.0. Asking for a permission is not a finding on its own - it is what the extension can do if it chooses to. The current listed version is 14.16.0, which we have not unpacked yet.
Read and change your data on every site you visit
<all_urls> and 3 more
Run hidden pages in the background
offscreen
See the address and title of every tab you have open
tabs
Capture the video and audio of a tab
tabCapture
Add items to the right-click menu
contextMenus
Store data in your browser
storage
Schedule its own background tasks
alarms
Run its own code inside the pages you visit
scripting
Store an unlimited amount of data in your browser
unlimitedStorage
Read information about your CPU
system.cpu
Read how much memory your computer has
system.memory
Show a panel beside the page
sidePanel
Speechify version history
12.26.1
Mar 4, 2026
+27 more
14.14.0
Nov 3, 2026
14.15.0
Nov 12, 2026
14.16.0
Nov 19, 2026
Where Speechify sends data
- firestore.googleapis.com/…3 calls
From its background script · 5 other extensions
- api2.amplitude.com/2/httpapi1 call
From its background script · 23 other extensions
- api2.amplitude.com/identify1 call
From its background script · 23 other extensions
- cdn-global.configcat.com/configuration-files/pmbZCPK580aDAL-QBTlBpg/…1 call
From its background script · 1 other extension
- diagnostics.api.speechify.com/logs1 call
From its background script · only this extension
- growthbook.cdn.speechify.com/api/features/…1 call
From its background script · 1 other extension
- identitytoolkit.googleapis.com/v1/accounts:lookup1 call
From its background script · 9 other extensions
- identitytoolkit.googleapis.com/v1/accounts:signUp1 call
From its background script · 9 other extensions
- payment.api.speechify.com/subscriptions/…1 call
From its background script · 1 other extension
- payment.api.speechify.com/users/update1 call
From its background script · 1 other extension
- t1.gstatic.com/faviconV21 call
From its background script · 31 other extensions
- t2.gstatic.com/faviconV21 call
From its background script · 34 other extensions
- t3.gstatic.com/faviconV21 call
From its background script · 32 other extensions
- user-profile.api.speechify.com/settings/user-documents1 call
From its background script · only this extension
- user-profile.api.speechify.com/settings/user/…1 call
From its background script · only this extension
- vms.api.speechify.com/public-voices/get-by-scopes1 call
From its background script · 1 other extension
Chrome Web Store listing
- Versions
- 14.16.0 latest of 31 seen since March 4, 2026
- Store rating
- 4.6 from 22,324 ratings
- Last updated
- June 15, 2026
- Size
- 23.24 MiB
- Privacy policy
- www.speechify.com
