How do we connect a live feed to super-gpu?

Give super-gpu a stream URL, message queue or API to pull the feed from your cameras or servers; push the stream to an endpoint super-gpu provides behind a VPN; run an on-premise node beside the cameras so the feed never leaves your network; or call the super-gpu AI services directly from an API.

How are results returned?

By SCP behind a VPN directly to your server, through your own API, as SCP download details behind a VPN, or on the NAS or DAS you provided, returned with the results on it.

Can we bring our own model?

Yes. You can bring your own model to run on super-gpu hardware, and super-gpu AI advisors can help select the best model, pipeline or hardware for the process.

Which live stream formats are supported?

Any operating system, encoding and live stream format is supported.

Input type — Live feed

AI models for Live feed

Eleven services that read a stream as it arrives and return structured output — who and what is in frame, what is being said, and an alert when a rule trips. One camera or a whole estate, on the same dedicated cluster.

The right model for the job

Our AI advisors may assist you to select the best model or pipeline for the process or offer the most efficient hardware to perform the process.

Of course, you can bring your own model to run on our hardware.

In case you like to use your on-premise servers cluster or a certain cloud we may provision the needed services and build the pipeline.

One model chosen from the catalogue, matched to your workload and hardware

AI services for Live feed

Our service catalogue include vast selection of services.

Part of the services based on stable AI models and part of the services based on our native code.

Each service can use several models and methods. After a short discussion we can decide on the right pipeline for the process.

Find a service

People and faces

Face recognition: Faces matched live against a face database you hold and control.
Crowd counter: People counted in dense scenes where bodies overlap.
People entrance / exit counter: Movement across a line or doorway counted in each direction.

Objects and text

Live object detection / tracking: Objects located, labelled and followed across the stream in real time.
Live OCR: On-screen and in-scene text read as the feed runs, with timecodes.

Audio and speech

Video to audio: The audio track separated from the stream as it arrives.
Video audio to text: Speech transcribed live, with timings and speaker turns.
Narrator extraction - transcription: Only the narrator track isolated and transcribed.
Audio noise suppression: Background noise removed and speech brought forward on the live track.

Safety and hidden data

Live stream moderation / visual policy alerts: Frames checked against a policy you define, with alerts as they trip.
Live steganography - hide small text/data in video frames: A small payload carried inside the frames as they are encoded.

How to connect your live feed?

We support any OS / Encoding and format for live streams.

You can provide us a stream URL and details and we get the stream from there or we can provide you a URL to steam the data to our servers.

You can run an on-premise node, so the feed never leaves your network.

How to get the results?

We can provide the results with SCP (behind VPN) directly to your server, to use your API for results, send you SCP (behind VPN) details to download the results or stream the results to your server.

Other input types

Pictures Faces, objects, counting, captioning, quality, hidden data. AI models for Pictures →
Documents Extraction, classification, redaction, question answering. AI models for Documents →
Video files Tracking, transcription, subtitles, summarization. AI models for Video files →
Audio files Transcription, diarization, separation, summarization. AI models for Audio files →
Text files Summarisation, extraction, translation, PII detection. AI models for Text files →