Is my audio encrypted before it leaves my machine?

Yes. The Privatemode proxy runs locally and encrypts all audio data before sending it to the Privatemode service. It also performs remote attestation to verify the integrity of the Privatemode service, ensuring end-to-end protection for every transcription request.

Does Privatemode store my audio or transcripts?

No. Privatemode never learns from your data, and no audio or transcript content is retained after processing. All transcription requests are processed using confidential computing, and only operational metadata such as token usage, timestamps, and request status is kept for billing and monitoring.

Do I still need the Privatemode proxy with Meetily?

Yes. The proxy is a lightweight local process that handles encryption and remote attestation. It verifies that the Privatemode service is running in a genuine confidential computing environment before sending any audio. Meetily connects to the proxy as if it were a standard OpenAI-compatible STT endpoint.

How does this compare to Meetily's default local transcription?

Meetily's default local transcription processes audio entirely on your device, which is private but limited to the model size your hardware can run. Privatemode runs cloud-grade STT models in a confidential computing environment, giving you better accuracy without handing your audio to a conventional provider in plaintext.

Integrating Privatemode AI with Meetily

Meetily records, transcribes, and summarizes meetings on your own machine. Routing transcription through Privatemode gives it full-size Whisper instead of a laptop-sized model, with audio that stays encrypted in memory even while it is processed.

Introduction

The challenge

Voice is not ordinary data

A recording identifies who is speaking, and the people in the meeting agreed to be recorded, not to have their voices sent to a transcription service. Meetily therefore transcribes locally, but a laptop-sized model struggles with accents, technical vocabulary, and people talking over each other.

The solution

Full accuracy, still confidential

Meetily sends audio to the Privatemode proxy instead of a local model and gets Whisper large-v3 at full size, the same model that local setups can only run in reduced form. The audio is encrypted before it leaves and processed in a hardware-isolated environment whose memory stays encrypted.

Benefits

Why use Privatemode AI with Meetily?

Full-size Whisper, no GPU needed

See models

End-to-end confidentiality

Learn how

Free tier available

How to get started

How to set up Privatemode in Meetily

Get your API key

If you don't have a Privatemode API key yet, you can generate one for free here.

Run the Privatemode proxy

The proxy verifies the integrity of the Privatemode service using confidential computing-based remote attestation. The proxy also encrypts all data before sending and decrypts data it receives.

Select the proxy as transcription provider

In Meetily, open Settings, then Transcription, and select OpenAI-Compatible. Enter http://localhost:8080/v1 as the server URL, wait for the model list to load, and select whisper-large-v3. The API key can stay empty or hold any value, because the proxy holds your real one. Select Test Connection before your first recording.

Walk through our interactive demo

FAQ

Frequently asked questions about using Privatemode with Meetily

Yes. Meetily supports custom OpenAI-compatible endpoints. You configure the transcription API base URL in Meetily's settings to point to any compatible service, including the Privatemode proxy running locally.