Privacy

Auditext has no accounts, no sign-up and no database of users. Here is exactly what happens to your data.

Text you convert with AI voices

When you press Generate speech, the text is sent in segments to our server and on to a speech model through Vercel AI Gateway (currently Google’s Gemini TTS, with OpenAI TTS as a fallback). The audio comes back to your browser, where it is joined and encoded. We do not store your text or audio. The AI providers process it under their API terms, which do not allow training on API data by default.

Script writer and casting assistant

The brief or draft you submit is sent to OpenAI’s gpt-6-luna model through Vercel AI Gateway to generate a response, and is not stored by us.

Files you upload

TXT, PDF and DOCX files are read inside your browser. The file itself is never uploaded. Only the text you choose to render is sent, and only when you press Generate.

Photos and scanned pages

When you upload a photo or ask Auditext to recognise text in a scanned PDF, each page is converted to an image in your browser and sent to OpenAI’s gpt-6-luna vision model through Vercel AI Gateway to read the text. The images are not stored by us.

Read aloud and device voices

These use your operating system’s built-in voices. Nothing is sent to us. (Some browsers route their own “online” voices through the browser maker’s servers.)

Saved in your browser

To save you retyping, your latest draft, chosen voice, pace, bitrate and last script are stored in this browser’s localStorage under keys starting with auditext:. They never leave your device.

Clear everything Auditext saved

Analytics

We use Ahrefs Web Analytics, a cookieless analytics tool, to count page views and referrers. It does not use cookies or build personal profiles.

Abuse limits

To keep the free service running, our server counts requests per IP address in memory for up to an hour to enforce fair-use limits. These counts are not logged or stored.