Privacy Policy

Last updated: 8 September 2026

Speech is a dictation app that turns what you say into clean, written Hinglish text and inserts it into whichever app you are using. This policy explains what information the app collects, why, and the choices you have. Speech is operated by Creativefuel Private Limited ("we", "us"), Indore, Madhya Pradesh, India.

1. Information we collect

Aside from the short pre-cursor snippet described above, the text you select in Agent Mode, and Screen Vision if you have turned it on, we do not collect your contacts, location, photos, or the contents of the screen or apps you use. The accessibility permission is used solely to place your dictated text at the cursor in the field you are typing in and to read that snippet (see Section 5).

We do not use cookies for tracking and there is no advertising or analytics code on this website. When you sign in, your session token and your dictation key are stored in your browser's local storage so you stay signed in; signing out removes them.

2. Microphone and recording

The microphone is used only to capture speech while you are actively dictating (holding the dictation button or bubble). Speech does not record in the background or listen when you are not dictating, unless you explicitly start a meeting recording or enable the optional wake-word feature.

Meeting notes: when you start recording a meeting, Speech captures your microphone and, with your Mac's permission, call audio. Audio is streamed for transcription and is not saved by the meeting service. On Mac version 0.9.43 and later, Speech also saves a local recording with your microphone and call audio in separate channels, so you can play it back and review your notes. This local recording is kept in both Standard and Privacy Mode. Text is processed online to produce the transcript, summary and action items. In Privacy Mode, meeting notes are saved on your Mac; snapshots sent for processing are not saved to the cloud meeting archive. Outside Privacy Mode, transcripts and notes are saved in your Speech account until you delete them. Recording stops when you press Stop or the meeting duration limit is reached. Let participants know before recording.

Local meeting audio: recordings remain in Speech's application support folder on the Mac where they were recorded until you remove the files. Speech does not automatically upload this saved audio file or delete it on a timer. Use Show file in a saved meeting to find the recording in Finder. Deleting a meeting transcript, signing out or deleting your Speech account does not delete this separate local audio file; remove it in Finder when you no longer need it. Earlier meetings have no local recording unless audio was saved when they were recorded.

3. How your data is used

• To transcribe your speech into text and deliver it back to you.
• To provide your dictation history within the app and your account.
• To maintain, secure, and improve the accuracy and speed of the service.

We do not sell your personal data, and we do not use your dictation content for advertising.

4. Third-party processing

To transcribe and format your speech, audio and/or text are processed by the following service providers acting on our behalf:

• Sarvam AI: speech-to-text transcription. Receives your audio.
• OpenRouter: routes model requests on our behalf. Depending on the path a dictation takes, the model that runs is operated by Google, which may receive the audio itself, or Groq, which receives the transcribed text.
• OpenAI: receives selected text when you use a text command or rewrite. Never audio.

These providers process the data only to perform transcription and formatting for us.

Three more providers support the service without touching what you dictate:

• Amazon Web Services: hosting. Our servers and databases run in AWS's Mumbai region (ap-south-1), in India.
• ZeptoMail (Zoho): sends your sign-in codes and any service email. Receives your email address, never your dictations.
• Google: if you choose "Continue with Google" to sign in, Google confirms your identity to us and we receive your email address from them. This is separate from Google's role as a model provider above.

If you connect an optional third-party integration yourself (for example Swiggy, for Agent Mode ordering), we hold an access token for that service, encrypted, so the feature can act on your behalf. You can disconnect it at any time, and disconnecting deletes the token. These integrations are off unless you connect them.

5. Accessibility permission (macOS, Android) and keyboard shortcut (Windows)

On macOS, Speech uses the Accessibility permission for one purpose: dictation. It places your dictated text at the cursor in whichever app you are in, and reads the short snippet of text immediately before that cursor so spacing and capitalisation come out right. It does not read the rest of the document, does not read other apps, and collects nothing when you are not dictating. Speech also registers a system-wide shortcut so you can dictate without leaving the app you are working in; like any global shortcut it sees key events across the system, but Speech acts only on the shortcut you have chosen and never logs, stores or transmits what you type.

Speech uses Android's Accessibility Service for one purpose: dictation. It detects when you focus a text field (so the dictation bubble appears), inserts your dictated text at your cursor, and reads a short snippet of text immediately before the cursor so the result is spaced and formatted correctly. It does not read other apps or the rest of your screen, does not run when you are not dictating, and never appears in password or payment apps. When dictation is not active it collects nothing.

On Windows, Speech registers a system-wide keyboard shortcut so you can dictate without leaving the app you are working in. Like any global shortcut, the hook receives key events across the system, but Speech only acts on the shortcut you have chosen. It does not log, store, or transmit what you type. To place the finished text, Speech copies it to your clipboard, sends a paste keystroke to the app you have focused, and then puts your previous clipboard contents back. It does not read the contents of other applications.

5a. Screen Vision (Agent Mode)

Agent Mode can answer questions about what is on your screen ("is page pe API key kahan hai"). To do that it needs a picture of the window you are looking at, so this is the one feature that captures your screen, and it is off by default. Nothing is captured until you turn Screen Vision on yourself and grant your operating system's screen recording permission.

When it is on:

• Only the focused window is captured, not your whole screen, and only on a request that actually refers to the screen. A plain dictation never sends an image.
• Speech never captures a password manager, keychain, wallet or banking app, and never its own windows.
• The image is held in memory, sent to the model that answers your question, and never written to disk on your device.
• Turn it off in Settings at any time, or revoke the screen recording permission in your operating system, and capture stops.

5b. Agent Mode: the selection, and the short conversation memory

Agent Mode is the separate control that asks Speech to do something rather than type what you said. Two things reach our servers on those requests that a plain dictation never sends.

• The text you have selected. If you highlight a sentence and say "isko formal banao", that sentence is what we are being asked to rewrite, so it is sent with the request. Nothing is sent when nothing is selected.
• A short conversation memory. Your last few Agent Mode requests and the replies to them are kept for five minutes, so that a follow-up means something. It is scoped to the app you are working in, it is never used to build a profile of you, and it expires on its own. Saying "bhool jao" deletes it immediately, as does deleting your account.

Agent Mode requests are processed by the same providers listed in Section 4 and are subject to the same retention choice in Section 6 as your dictations.

5c. Connecting your Google account

Google sign-in uses your verified email address to create or open your Speech account. It does not grant access to Gmail, Calendar or Drive. Connecting Google is a separate, optional consent: it lets Meeting notes show your calendar events and, where Agent Mode is available, lets it work with your Gmail, Calendar, Sheets and Docs. You choose the Google account and permissions yourself.

• We hold your refresh token encrypted, associated only with your Speech account, and use short-lived access tokens to make requests. Disconnecting in Settings deletes the stored connection and revokes its Google grant. You can also revoke access from your Google account's security page.
• Calendar events are retrieved to display your meetings. Agent Mode reads Google data only for the request you make and passes relevant content to the model answering that request. A reply may be held in the short conversation memory described in Section 5b so you can ask a follow-up. Google data is not used to train models or for advertising, and is not shared with other Speech users.
• Nothing is ever sent, created or changed in your Google account without a confirmation you tap first.

Speech's use and transfer of information received from Google APIs follows the Google API Services User Data Policy, including its Limited Use requirements.

6. Storage, security, retention, and your Privacy Mode choice

Your data is transmitted over encrypted (HTTPS/TLS) connections and stored on secured servers located in India. You choose how long we keep the content of your dictations, in the app under Settings → Privacy:

• Standard. Your transcripts are stored on our servers for as long as your account exists, and may be used to improve Speech's accuracy and models. They are never sold, and never used to train anyone else's models. The voice recording itself is kept for up to 60 days and then deleted automatically. You can delete everything at any time (section 7).
• Privacy Mode. Your audio and transcripts are transcribed and then discarded immediately. Nothing is retained on our servers, and no dictation history is kept on your device.

Anonymous usage counts (for example the number of words dictated) are kept in either mode and contain no transcript text or audio. You can delete your account and all associated data at any time (see Section 7).

Pictures you asked Agent Mode to generate are kept for up to one year, with the words you used to ask for them, because the app has a page that shows you your own pictures and a picture you cannot find again is one you have to pay to make twice. Deleting your account deletes them.

Bug reports are kept longer than dictations, for up to one year, including any screenshot you attached. A screenshot attached to a bug is a record of a defect rather than a recording of your voice, and a year is how long a report stays useful while the defect is being fixed. They are deleted automatically after that, and Section 7 explains what happens to a report when you delete your account.

Nobody at Creativefuel can read your transcripts or play your audio unless you switch that on yourself, from your own account page, and no administrator can switch it on for you. Without it, what our own team can see about a dictation is when it happened, which app it went to, how long it was, how many words it produced, and whether it succeeded, which is what we need to fix problems.

7. Your choices and rights

• Delete everything in the app: Settings → Account → "Delete account & data" permanently erases your account and every dictation, transcript and recording stored for it, from our servers and your device. It is immediate and irreversible.
  One exception: if you sent us a bug report, the report itself stays in our engineering queue, with you removed from it. Your account link, your name and the device details attached to the report are erased along with everything else; what remains is the description of the problem, which is the part we needed in order to fix it.
• Or contact us: email support@creativefuel.io from your account's email address and we will provide or delete your dictations and account data for you.
• Choose what we keep: Privacy Mode (Section 6) is a switch in the app, and you can change it at any time. It applies from the moment you turn it on.
• Screen Vision is off until you turn it on, and turning it off stops any capture (Section 5a).
• Permissions: you can revoke microphone, notification, overlay, screen recording or accessibility permissions at any time in your operating system's settings, on macOS, Windows and Android alike. Some features will stop working without them.

8. Children

Speech is intended for users aged 18 and older and is not directed at children.

9. Changes to this policy

We may update this policy from time to time. Material changes will be reflected by the "Last updated" date above.

10. Contact and grievances

For any privacy request or question, contact us at support@creativefuel.io. We aim to reply within two working days.

If you are not satisfied with how we have handled a request, you can escalate it to our Grievance Officer under the Digital Personal Data Protection Act, 2023, at grievance@creativefuel.io. We will acknowledge a grievance within 72 hours and respond within 30 days.

Creativefuel Private Limited, Indore, Madhya Pradesh, India.
See also our Terms of Service.