Input type — Video files
AI models for video files
Sixteen services that read recorded footage and return structured output — who and what is in it, what was said, and a cleaner file back. One clip over an API, or a whole archive in a batch, 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.
AI services for video files
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.
{{ filterNote }}
People and faces
- Face recognition
- Faces matched against a face database you hold and control.
- Crowd counter
- People counted in dense scenes where bodies overlap.
- People entrance / exit counting
- Movement across a line or doorway counted in each direction.
- Queue length / dwell-time analytics
- How long people wait and how long they stay, per zone.
Objects and text
- General object detection and tracking
- Objects located, labelled and followed from frame to frame.
- Video OCR / text recognition
- On-screen and in-scene text read across the footage, with timecodes.
Audio and speech
- Video to audio extraction
- The audio track separated from the video as a clean file.
- Video audio to text
- Speech in the footage transcribed, with timings and speaker turns.
- Narrator to video - add supplied narrator audio
- Narration you supply mixed into the video and aligned to it.
- Narrator to video - generate narration from text
- A narration track generated from your script and laid over the video.
- Automatic subtitles / captions
- Timed subtitle files, burned in or delivered alongside.
Understanding and search
- Video summarization
- A long recording reduced to a written brief or a short cut.
- Video semantic search
- Find the moment by describing it, across a whole archive.
Quality and provenance
- Video upscale resolution
- Resolution raised on low-quality or legacy footage.
- Video frame interpolation / slow motion
- Frames generated between frames for smoother or slowed playback.
- Digital watermark / provenance embedding
- Origin and ownership marked into the footage so it survives re-encoding.
How to provide us video files?
We support any OS / Encoding and format for video files.
You can upload your video files with SCP (behind VPN) to a URL we provide.
You can provide us URL, MQ or any API and we will pull the video files directly from your server.
You can send a NAS or a DAS to our location.
You can use our AI services with an API.
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 send you back the NAS/DAS you provided with the results.
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 →
- Audio files Transcription, diarization, separation, summarization. AI models for Audio files →
- Live feed Counting, tracking, live transcription, PPE and queues. AI models for Live feed →
- Text files Summarisation, extraction, translation, PII detection. AI models for Text files →