Skip to content
Service status

Type to search

Data Flows · 6 min read

Transcription

How your audio file is handled, how your data is protected, and what information is shared with the LLM provider during transcription and summarization.

Transparency is central to us at Intric. When you use the Transcription feature to process and summarize recorded audio files, specific processes are in place to ensure your privacy and secure data handling.

The process from your audio upload to a finished transcription and summary occurs through a secure, SSL/TLS-encrypted interaction between the Intric platform (where your data is managed) and the LLM provider you have selected (e.g. Berget AI).

All transfers between Intric and its sub-processors occur over secure, encrypted connections.

1 / 5User records or selects an audio file

Step 1 — User records or selects an audio file

For live recordings: The audio is captured and stored entirely within the user’s browser, both during and after the recording. No audio data is sent to Intric at this stage — it stays on the user’s device until the user clicks Stop and save.

For uploaded files: The user selects a pre-recorded audio file from their device.

To protect your and your organization’s privacy, we apply the principle of data minimization. This means the sub-processor only gets access to the content absolutely necessary to perform the task — no user identity ever leaves your infrastructure.

We have strict zero data retention clauses in all our contracts with language model sub-processors. This guarantees that your audio files and the generated texts are never saved by the provider after the response is returned, nor is the information used to train their AI models.

In the table below, you can see exactly what data is sent to the sub-processor and what does not leave Intric’s servers.

Sent to the transcription modelNot sent to the transcription model
  • The recorded audio file / audio data
  • System instructions for transcription and summarization
  • Personal data about the user in Intric interacting with the assistant, provided it does not appear in the message to the assistant:

    • Name
    • Email
    • IP address
    • Organization affiliation

Transcription history follows the same principles as other assistant interactions — depending on whether the assistant is a personal assistant or in Spaces, the Creator or Admin controls deletion.

Metadata about how users use features in Intric can be stored for longer periods and is available to administrators.