Explore the world around you.

Speak with ease, see with vision.

Sen is a real time visual intelligence that connects your phone camera to a Large Language Model (LLM).

Interface

Superpower your day.

Our interface is built for effortless interaction. Open the camera, start speaking and Sen will handle the rest.

engine

Quietly Powerful.

Under the hood, Sen is powered by the latest realtime artificial intelligence. The multimodal AI is fine-tuned to provide natural conversations and sharp visual insights. From conquering creative tasks to solving complex problems, Sen is a trusted collaborator, optimized for low-latency performance.

Memory

Your friends might get jealous.

In PRO mode, Sen gets smarter with every video interaction, crafting a memory that drives sharper and more tailored insights. Whether you’re exploring the outdoors, cooking at home, or working on a project, Sen delivers intelligent real time support.

Unlock your genius.

Basic
Best for beginners or casual users
$25/mo
  • Up to 100 messages/month
  • Basic Customization
  • Email Support
Start for Free
7-day free trial
Recommended
PRO
For freelancers & professionals
$49/mo
  • Memory
  • Unlimited Usage
  • Priority Support
  • Early Feature Access
Go PRO
7-day free trial

Limited memberships available—join the waitlist to secure your spot.

[email protected]

© Sen Intelligence. All rights reserved.

Sen should not be considered a substitute for a health professional's advice; should not be used to diagnose a health condition.

Thank you!

Your journey with Sen begins here.
We’re dedicated to offering you an exceptional experience that listens, adapts, and improves your everyday.

Give your employees real-time answers.

Superpower your workforce with advanced visual intelligence tools that improve accuracy, quality and production.

real world solutions

Making hardwork easy.

Sen is powered by the latest realtime artificial intelligence. Using video and voice input, our technology can understand the task at hand, solving complex problems on the job.

knowledge base

Your data

We partner with your data team to integrate your specific knowledge base. We then use a sophisticated retrieval system to generate lightning fast answers, with 99% relevancy. This translates into instructions, diagrams, and job specific information all available at your finger tips with video and voice feedback.

Sen

Vision

I've spent the past four months building a realtime visual intelligence app that connects your phone camera to a multimodal LLM. It uses the open-source Pipecat framework and WebRTC (daily). The ios client connects via webRTC to stream video+voice input to the python server. Frames are captured at 1fps and sent via web socket to a multimodal LLM.It's similar to ChatGPT Advanced Voice but includes grounding with Google search, which is auto triggered through a function call if the bot doesn't know the answer.The project has posed many difficult challenges for a first time builder and I can't say for certain that my stack will be the long term approach. All the current players are using a similar form of webRTC streaming for voice+voice input. However, as models get closer to the metal, and different vision and object detection technologies improve, a Tradition stt/tts coupled with structured data transmission, may offer more sustainable and low latency solutions. What stack do you see as a better solution for video assistants moving forward?I warmly welcome beta testers to try it. I built this product with $0 in VC funding, a dream, and some trusty sonnet 3.5 vibe coding in Cursor. If you want to collaborate or work on scaling issues with me please reach out.Join the waitlist at www.withsen.com
[email protected]

Sen
Sen