Privacy Policy

The short version

• Your file is never uploaded. The video or audio you choose is read and transcribed inside your own browser. This site has no server that could receive it.
• No account, no profile, and no advertising or affiliate links today. The page’s own code stores two small entries that make it work — which model you used last, and a marker that is deleted as soon as a transcription finishes — and, separately, keeps the downloaded speech model in the browser's own cache. The section below says exactly what each one is.
• Two analytics run, and one of them sets cookies. Cloudflare Web Analytics counts page views without using cookies. Google Analytics also runs on every page, and it does set cookies — _ga and _ga_KJ155PR9B7 — to tell one visitor from another. Both are described below.
• No advertising and no affiliate links are on this site today. Both are planned. Before either appears, this policy will be updated to describe it, and the date at the top of this page will change.

Your video and audio files

When you pick a file, the browser reads it directly from your device. The audio is decoded and the speech is transcribed in your browser, using a model that is also running in your browser. The file itself is never transmitted anywhere — there is no upload step, no queue, and no copy of it on any server belonging to this site.

You do not have to take that on trust. The whole application is a set of static files you can inspect, and the network activity of a transcription run is small and observable: apart from the model download described in the next section, the page sends short view-count reports to two analytics endpoints — Cloudflare Web Analytics, which is this site's own and sets no cookies, and Google Analytics, which sets the two cookies named above. Neither carries any part of your file.

The one thing that is downloaded: the speech model

The speech recognition model does have to be fetched, because it is far too large to ship inside a web page. The three models the tools offer by default are served from this site's own address (reeltotext.app/models/…), so the first transcription downloads them from the same domain as the page you are reading. This is an ordinary download of a public file — the same file every visitor receives — and it carries nothing about you or your file. The fourth option in the model menu, whisper-small, is roughly 240 MB and is not stored here: if you select it, your browser fetches it from a third-party model host, Hugging Face (huggingface.co, with the large files served from its CDN at us.aws.cdn.hf.co), and that host may not be reachable from your network.

Your browser then keeps that model in its own file cache — the Cache Storage API, not localStorage — so later transcriptions do not download it again. You can clear it at any time through your browser's site-data settings; the only consequence is that the next run downloads the model again.

Analytics

This site uses Cloudflare Web Analytics to count page views and measure how quickly pages load. The measurement script is served from static.cloudflareinsights.com and reports to this site's own address. It is included because it is the least intrusive option available: Cloudflare states that Web Analytics "does not use any client-side state, such as cookies or localStorage, to collect usage metrics" and that it does "not 'fingerprint' individuals via their IP address, User Agent string, or any other data for the purpose of displaying analytics" (Cloudflare, Web Analytics product documentation). What it reports is aggregate: page views, referrers, approximate country, and page-load timing. Cloudflare states that it does not log query strings, and that unsampled beacon data is retained for 7 days before being aggregated down.

This site also uses Google Analytics 4, provided by Google. It runs on every page, including this one, through a script loaded from googletagmanager.com. Unlike Cloudflare Web Analytics, Google Analytics sets cookies in your browser:

• _ga — distinguishes one visitor from another. Lasts 2 years.
• _ga_KJ155PR9B7 — keeps the session state for this site’s Google Analytics property. Lasts 2 years.

Google Analytics reports page views, referrers, approximate location, device and browser type, and how visitors move through the site. How Google handles data from sites that use its services is described at policies.google.com/technologies/partner-sites, and Google Analytics can be blocked across all sites with Google’s own browser add-on at tools.google.com/dlpage/gaoptout.

Neither analytics tool receives your file. Transcription happens in your browser, and neither tool is given the audio, the video, or the resulting transcript.

Apart from these two, there is no other analytics on this site — no advertising pixels, no session recording.

Cookies and storage in your browser

The page’s own code writes nothing to sessionStorage and creates no database in your browser; it writes the two localStorage entries listed below, and separately keeps the downloaded model in the browser's Cache Storage, which is a different storage area from localStorage. Separately, Google Analytics sets the two cookies named in the Analytics section above — _ga and _ga_KJ155PR9B7. Those two are the only cookies this site causes to be set. Those two entries and the cached model are not tied to your identity, are not sent anywhere, and are not used to recognise you on any other site; the Google Analytics cookies are set and read by Google’s script, as described above.

• The cached model described above — the downloaded model files, kept in the browser's Cache Storage (caches) rather than in localStorage, so you do not have to download the speech model twice. It is the largest thing this site puts on your device: the default whisper-base is about 76 MB.
• One preference, stored under the name reeltotext.model, recording which speech model you used last. It exists so the page opens on the model you used last time, and so a device that cannot fit the default model is not made to download it and fail on it again on every visit. Its value is that model's name, plus a short note when the page itself stepped down to a smaller model because your device ran out of memory for the one you asked for.
• A run marker, stored under the name reeltotext.run, written when a transcription starts and deleted the moment that run ends — whether it succeeded, failed, or was stopped by the page itself. It covers the one case where a run ends without the page being told: a tab the browser closes to free memory, a phone that restarts, a force-quit. If the marker is still there when you come back and no live page is still running that job, the page tells you that the last run did not finish and removes it at that point — a run that is still going in another tab is not reported as a failure.

No consent banner is shown

Advertising (planned, not yet served)

This site is free and has no accounts or paid tier. To cover the cost of the domain and hosting, third-party advertising and affiliate links are planned: advertising most likely through Google AdSense or a comparable network, and links to transcription services that pay this site a commission when a visitor signs up through them. No advertising is served and no affiliate link is present on this site at the moment you are reading this. This section is here so the plan is not a surprise later.

When advertising does start, this is what will change, and this policy will be rewritten to say so plainly before it happens:

• Ad network code will load on the page, and those third-party vendors may set their own cookies or read device identifiers in order to select and measure ads. Those cookies are set by the vendor, not by this site.
• Affiliate links may appear in pages. Following one takes you to another company’s site, and that company may set its own cookies and may record that you arrived from this site. Where a link earns this site a commission, that will be disclosed on the page carrying it. An affiliate link does not change what the tools do with your file.
• Google and other third-party vendors may use cookies to serve ads based on a visitor's prior visits to this site or to other sites.
• Where required by law, a consent notice will be shown before any non-essential cookie is set, and advertising cookies will not be set unless consent is given.
• You will be able to opt out of personalised advertising through Google's Ads Settings at adssettings.google.com, and you can read how Google uses data from sites that use its services at policies.google.com/technologies/partner-sites.
• The tools themselves will not change: your file will still be transcribed inside your browser and will still never be uploaded. Advertising does not need your file and will not receive it.

Until that happens, none of the above is in effect, and this page will not claim otherwise.

Other companies involved

These service providers are involved in serving this site, and none of them receives your file:

• Cloudflare hosts the site and provides one of the two analytics tools described above. As with any web host, its servers process the requests needed to deliver pages to you, which necessarily includes your IP address.
• Google provides Google Analytics, described above. Its script is loaded by your browser, and the cookies it sets are set and read by Google.
• Hugging Face serves the whisper-small model file if you select that option, as described above. That is a download from its servers to your browser; nothing is sent back. The three smaller models are served from this site itself and involve no third party at all.

This site is independent and is not affiliated with TikTok, Instagram, Meta or YouTube, nor with OpenAI, Hugging Face or the Transformers.js project.

Children

This site is a general-purpose utility and is not directed at children, and it does not knowingly collect personal information from children. The analytics described above measure visits in aggregate; they are not used to build a profile of any individual visitor.

Your choices

This site holds no account for you and stores nothing about you under your name, so there is no personal data held by this site to access, correct or delete. Analytics data about visits is held by Cloudflare and by Google under their own policies rather than by this site; the links above explain how to reach or opt out of each. Clearing this site’s data in your browser settings removes the cached model, the stored preference and the Google Analytics cookies together; the next run will ask your browser for the model again. The run marker needs no action — it deletes itself as soon as a run ends. If you believe this site has handled something incorrectly, write to the address on the contact page and it will be looked at.

Changes to this policy

This policy will be updated whenever what the site actually does changes — in particular when advertising begins. The date at the top of this page is the date of the current version. The two tool pages used to state that the site ran no analytics; that stopped being true once Cloudflare Web Analytics was enabled, so those pages have been corrected alongside this one. This page itself used to state that the site wrote nothing to localStorage; that stopped being true when the page began remembering which speech model you used, so the storage section above was corrected at the same time. It has been corrected once more since: the page also records that a transcription has started, so that a run the browser ended without telling the page can be explained on the next visit. It has been corrected again on 23 September 2026: this page previously stated that the site set no cookies and ran no Google Analytics. Both stopped being true when Google Analytics was added, so the Analytics and storage sections above were rewritten at the same time, and the advertising section now also covers planned affiliate links. It has been corrected once more on 24 September 2026: this page and the tool pages each described the network activity of a run as a single analytics report, and that stopped being true once Google Analytics was added to every page — the three tool pages, their frequently-asked questions and the structured data behind them have been corrected in the same round. It has been corrected again on 27 September 2026: this page stated that the speech model was downloaded from Hugging Face, and the about page repeated it. That stopped being true once the three default models began being served from this site's own address, so the model section and the service-provider list above were corrected together with the about page in the same round, and both now name the one case where a third-party host is still used. It has been corrected again on 13 October 2026: the storage section described the cached model as one of the site's localStorage entries, and the summary above called the site's stored data 'three small entries'. Measured on the real page: a clean run on the default model writes no localStorage entry at all, and the downloaded model — about 76 MB for the default — is kept in the browser's Cache Storage instead. The section above now names each mechanism, and the storage check that reconciles this page against the running app now reads the Cache Storage as well as localStorage.

Contact

Questions about this policy: see the contact page.