About Pexip Private AI and AIMS

The Pexip Private AI platform allows you to access Pexip's AI-powered features (such as live captions) in a secure environment. It uses Pexip's AI Media Server (AIMS), a self-hosted standalone virtual machine, which you deploy on your own hardware or private cloud environment, giving you complete control of your data.

The Pexip Private AI platform is deployed alongside, but entirely separately to, your Pexip Infinity platform. You configure Pexip Infinity to integrate with Pexip Private AI where required for supported features.

This release of Pexip Private AI runs on AIMS v1 and supports Pexip Infinity's live captions feature.

Supported hardware, software and environments

Deployment environments

Pexip provides the AI Media Server (AIMS) software as an OVA template suitable for deployment on VMware ESXi, and as an Amazon Machine Image (AMI) for deployment on Amazon Web Services (AWS).

For step-by-step guides for installation in your chosen environment, see:

Pexip Infinity versions

The table below shows the minimum versions of Pexip Infinity and AIMS required in combination to support each AIMS feature.

Feature Pexip Infinity AIMS
Live captions (speech to text) — per VMR v36 v1
Support for en-US, es-US, de-DE, fr-FR v36 v1
Word boosting v36 v1
Live captions history in Webapp3 v37 v1
Multiple AIMS servers v37 v1

NVIDIA GPU

The AIMS VM requires complete control of all GPUs assigned to it — the GPUs cannot be shared with any other VM.

The following NVIDIA GPU models are supported:

  • NVIDIA L4
  • NVIDIA A100
  • NVIDIA H100

If you are unsure about compatibility with a given GPU, please contact your Pexip authorized support representative.

Host hardware

For on-premises deployments, host hardware must meet the following minimum specifications for each card:

GPU CPU RAM Storage
L4 8 cores 32 GB 75 GB SSD (200 GB recommended)
A100 12 cores 32 GB 75 GB SSD (200 GB recommended)
H100 24 cores 64 GB 75 GB SSD (200 GB recommended)

These requirements may change in future versions.

For all other on-premises deployments, please contact your Pexip authorized support representative for guidance.

For cloud deployments, your service provider will supply sufficient CPU and RAM to match the selected instance type and GPU quantity.

Capacity planning

When live captions are enabled for a VMR, AIMS receives the audio stream from Pexip Infinity, which it transcribes and returns as a text stream. Pexip Infinity then provides the text to all users who have enabled live captions. AIMS supports simultaneous transcription of up to the following number of audio streams:

  • L4: 80 streams per GPU

  • A100: 160 streams per GPU

  • H100: 300 streams per GPU

In each case, the maximum number of supported GPUs per server is 8.

See About system locations and AIMS for information about the Pexip Infinity capacity requirements.

Licensing

Pexip Private AI is a licensed optional feature within the Pexip Infinity platform. When it is enabled, you create connections to one or more AIMS servers by configuring their details under the media processing servers option.

For more information, contact your Pexip authorized support representative.

AI model cards

The table below lists the models used within AIMS, and provides links to NVIDIA's AI model cards (which are documents that provide detailed information about each model, including the training dataset, intended use, and other compliance information).

Acoustic models
English https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/parakeet-ctc-riva-0-6b-en-us/explainability
Spanish https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_es_us_conformer/explainability
German https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_de_de_conformer/explainability
French https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_fr_fr_conformer/explainability

Each language also uses its own Language Model, Punctuation and Capitalization Model, and Inverse Text Normalization Model.

Security considerations

AIMS runs on a standalone server which you can deploy in your own secure environment. All communication between AIMS and Pexip Infinity is over a secure (encrypted and authenticated) link.

When the live captions feature is enabled:

  • The AIMS deployment receives an audio stream from Pexip Infinity, and returns the transcription text stream to Pexip Infinity, over this secure link.
  • The audio and the corresponding captions generated from the audio are only stored temporarily in memory on the AIMS server, and the memory is immediately freed up when processing is complete.
  • The transcription text received by Pexip Infinity is provided to all meeting participants who have enabled live captions. Participants have the option to view captions either as ephemeral text overlaid on the main video, or from the Live Captions History panel, which provides a continuously updating view of all captions received while the participant has live captions enabled and is connected to the meeting. In the latter case, if a participant leaves and then rejoins a call, they will only see the captions shown since they rejoined.

  • Pexip Infinity does not log or retain the contents of any live captions transcripts.

More information

Release notes

Version Release date Description
v1.0 12 November 2024 Initial release