Categorical emotions
Scores text across emotions such as joy, sadness, anger, fear, surprise and disgust, with a top label.
CatalogLatency Typically 0.5–2 seconds Async false Rate Limit Per API key Max Input A few thousand characters per text
cn8/text-emotion
Emotion Detection classifies text into categorical emotions (joy, sadness, anger,
Learn more about Emotion Detection Text NLPsyncInstant previewtextanalysisnlp
Try it
Texts to analyzeOne text per line.
Result
Results show up here
The sample input is ready — just hit Run.
Overview
Emotion Detection classifies text into categorical emotions (joy, sadness, anger, fear, surprise, disgust, and more) so you can read the emotional tone of reviews, support messages and social posts.
Temporarily unavailable: this endpoint is offline while we finish work on it. In the meantime, combine Sentiment Analysis (for positive/negative/neutral polarity) with Zero-Shot Classification (using emotion labels you provide) to get the same result. See the workaround guide below. Calls to this endpoint are not billed while it is unavailable.
Key capabilities
Emotional tone at a glance
Turn free-text feedback into a clear emotion signal for dashboards and routing.
Simple JSON API
Send a texts array and get a structured result back — no setup or training.
Pay per request
$0.002 per request once the endpoint is available again.
When to use it
Support prioritization
Flag angry or frustrated customers so they get a faster response.
Content analysis
Measure emotional tone across reviews, social posts and survey responses.
Input & output
input
A texts array of strings to analyze.
JSON body
output
A result per text with an emotion label and score (available when the endpoint is back online).
JSON
Guides & tips
Workaround: Sentiment + Zero-Shot Classification
While Emotion Detection is unavailable, you can recreate it with two endpoints you control:
- Send your text to Sentiment Analysis (
text-sentiment) to get positive / neutral / negative polarity and a star rating. - Send the same text to Zero-Shot Classification (
text-classify) with your own emotion labels, e.g.["joy", "sadness", "anger", "fear", "surprise", "disgust"], to get the top emotion plus a score for each. - Together these give you both an overall sentiment and a categorical emotion.
Tips
- Choose emotion labels that match your use case — you are not limited to the six basic emotions.
- Keep labels in the same language as the text you are analyzing for best results.
Specs
Schema
Request body
textsrequiredarray<string>Array of texts to analyze.
Pricing
Billed per request when available. No charge while the endpoint is temporarily unavailable.
| Service | Unit | Price |
|---|---|---|
| Emotion Detection | item | $0.002/request |
Temporarily unavailable — no charges are incurred until it returns.