Robots/Parts/AI model
Built-in multimodal model
An AI model that can understand both speech and pictures, so a robot can be talked to and can describe or respond to what it sees. Unitree says its R1 humanoid is integrated with a large multimodal model for voice and images, but does not say which model it is or who makes it.
- 1 of 10
- robots in the database
- Not named
- made by
- AI model
- brain layer
- Not public
- price
Key numbers
- Model and supplier
- not named by Unitree
- Understands
- voice and images
Source: Unitree, R1 product page (unitree.com)
Strengths and trade-offs
Our analysisStrengths
Lets an owner talk to the robot in ordinary language.
Can link what it hears to what it sees, such as answering a question about an object.
Borrows the abilities of a large model without the robot maker having to build one.
Trade-offs
Unnamed, so nobody can tell how capable it is or where voice and pictures are sent.
A large model usually runs on a server, so it probably needs an internet connection.
It handles talking and understanding. It does not control how the robot walks.
Why robot makers choose it
Our readA low-cost humanoid sold to the public needs features people can enjoy on day one. Talking to it and asking about what it sees is easy to show off, and connecting an existing model is far cheaper than building one.
This is our reasoning from the public facts. No maker has confirmed it.
Robots using it
This list covers only the robots researched so far. A robot missing here may still use this part.
Numbers and listed prices on this page come from the sources shown. Anything marked as our analysis, our read or our estimate is our own view and has not been confirmed by any company. Last checked 14 Oct 2026. How we verify