Sensations in text, read in the open.

Open models that read the senses in text, with open weights on Hugging Face and an API any app can attach. Type any text and each sentence is scored for six senses.

Label set senses@0. The model learned from people's ratings of about 40,000 words. Vision runs high, because people rate most concrete words as somewhat visual: read it against the other senses.

Type a message, or start with one of these:

Nothing you type is stored. Enter to send, Shift+Enter for a new line.

Scores are a classifier's reading of the text, not a measurement of what anyone feels. The observer reads text only: a model saying “I feel cold” is a self-report in words, not a sign that it feels anything.

2Open models
6Senses
0.81Match with people's ratings, unseen words
32Texts per request
What the scores mean ↗
Build with it

One request. 6 scores.

Call the models through the API, or download the open weights from Hugging Face and run them yourself. Every result names the model and version that produced it.

Read the API guide →
POST /v1/classify
curl https://www.open-sensations.com/v1/classify \
  -H "Authorization: Bearer osn_live_…" \
  -H "Content-Type: application/json" \
  -d '{"blocks":[{"text":"The soup smelled of garlic."}]}'