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 v2 and supports Pexip Infinity's live captions feature.
In this topic:
- Supported hardware, software and environments
- Licensing
- Security considerations
- Risks and responsibilities
- Release notes
- Upgrading
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:
|
v36 | v1 |
| Word boosting | v36 | v1 |
| Live captions history in Webapp3 | v37 | v1 |
| Multiple AIMS servers | v37 | v1 |
|
Support for:
These are in addition to the 4 languages supported in AIMS v1. |
v36 | v2 |
| Language packs | v36 | v2 |
| Additional captions metadata (source and target languages) via API | v38 | v2 |
| Live translated captions (speech to translated text) via API — per VMR | v37 | v2 (tech preview) |
| Live translated captions (speech to translated text) via web app — per VMR | v38 | v2 (tech preview) |
| Speaker diarization (source participant) via API | v38 | v2 (tech preview) |
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.
Resilience / redundancy / scaling
For on-premises deployments we recommend running AIMS on a server with a single L4 GPU. Where additional capacity is required, we recommend deploying AIMS on multiple servers, each with a single L4 GPU. This provides resiliency and redundancy, and is usually more cost-effective than deploying AIMS on a single server with a higher-capacity GPU.
We test with A100 and H100 GPUs in supported cloud providers. If you have strong requirements that necessitate deploying AIMS on-premises with A100 or H100 GPUs, please note that our current server recommendations are based on limited real-world data and are subject to change. You should expect to work with your Pexip authorized support representative to determine the exact specifications appropriate for your environment.
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
NVIDIA AI models are continuously evolving, and CPU and GPU load requirements may change from one release to the next. As a result, server capacity, as well as transcription or translation performance, may vary across different languages and usage scenarios. You should anticipate that system resource demands and accuracy levels will fluctuate over time, and plan your infrastructure and operational processes accordingly. You must review release notes, test updates in relevant environments, and make appropriate adjustments to ensure service quality and reliability for your specific use cases.
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.
The number of audio streams that can be simultaneously transcribed will depend on the language model and the GPU. The table below can be used as a guide when planning server capacity, with the following caveat:
| Model | Language | L4 | A100 | H100 |
|---|---|---|---|---|
| ar-AR | Arabic | 60 | 120 | 160 |
| de-DE | German | 80 | 160 | 300 |
| en-US | English (US) | 80 | 160 | 300 |
| es-ES | Spanish | 80 | 160 | 300 |
| es-US | Spanish (US) | 80 | 160 | 300 |
| fr-FR | French | 50 | 100 | >150 |
| it-IT | Italian | 80 | 160 | 300 |
| ja-JP | Japanese | 20 | 40 | 100 |
| ko-KR | Korean | 60 | 120 | 200 |
| nl-NL | Dutch | 80 | 160 | 300 |
| pt-BR | Portuguese (Brazilian) | 80 | 160 | 300 |
| zh-CN | Mandarin | 30 | 60 | 100 |
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.
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.
Risks and responsibilities
The AIMS AI-powered captioning and translation service is designed to assist with communication, but should not be relied upon as the sole source of information in critical contexts.
When deploying AIMS, you are responsible for ensuring all end users are fully aware that accuracy cannot be guaranteed and will never be 100%. Variations in speech clarity, accents, background noise, technical limitations, and linguistic complexity may all impact output quality; therefore you must assess the risks and their impact on your organization when using this product. In critical contexts such as medical, legal, safety-related, or other high-impact scenarios, you must implement appropriate safeguards and independent verification measures to mitigate the risk of misunderstandings or unintended consequences.
You are also responsible for ensuring that all users are clearly informed that this system is powered by artificial intelligence, in accordance with any relevant AI transparency requirements in your jurisdiction.
Release notes
| Version | Release date | Description |
|---|---|---|
| v2.0 | 29 October 2025 |
See also the Known limitations for the current release. |
| v1.0 | 12 November 2024 | Initial release |
Upgrading
To upgrade from AIMS v1 to AIMS v2:
- Delete the existing VM and install a new VM (as per Deploying AIMS in VMware, Deploying AIMS in AWS, or Deploying AIMS in KVM).
-
Reconfigure AIMS according to Configuration and maintenance of the AI Media Server, taking note of the following:
- the Changes in functionality between v1 and v2
- in v2 you need to download and install the appropriate language bundles
- you must re-enable any word boost files.
- Run aims-config infinity-instance-add to reinstate the connection to Pexip Infinity.