{
"text": "This product is absolutely amazing! Best purchase I've made all year.",
"label": "positive",
"score": 0.9999
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27577/classify+text+as+positive+or+negative+with+a+confidence+score' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"text": "This product is absolutely amazing! Best purchase I've made all year."
}'
{
"results": [
{
"label": "positive",
"score": 0.9999
},
{
"label": "negative",
"score": 0.9903
},
{
"label": "negative",
"score": 0.9821
}
]
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27578/classify+multiple+texts+in+a+single+request' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"texts": [
"Great product, love it!",
"Terrible experience, never again.",
"It was okay, nothing special."
]
}'
{
"text": "I love spending time with my family and friends.",
"toxic": true,
"label": "toxic",
"score": 0.0009
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27579/detect+whether+text+is+toxic+or+harmful' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"text": "I love spending time with my family and friends."
}'
{
"detected": "fr",
"probabilities": [
{
"lang": "fr",
"prob": 1
}
]
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27580/detect+the+language+of+a+text+with+per-language+probability+breakdown' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"text": "Bonjour, comment allez-vous aujourd'hui?"
}'
{
"text1": "The cat sat on the mat.",
"text2": "A feline rested on a rug.",
"similarity": 0.553
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27582/compute+cosine+similarity+score+between+two+texts+using+sentence+embeddings' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"text1": "The cat sat on the mat.",
"text2": "A feline rested on a rug."
}'
{
"original": "Ths sentance has som speling mistaeks.",
"corrected": "Ths sentence has som spelling mistakes",
"misspelled": {
"speling": "spelling",
"mistaeks.": "mistakes",
"ths": "the",
"sentance": "sentence"
}
}
curl --location --request POST 'https://zylalabs.com/api/13314/text+intelligence+api/27584/detect+misspelled+words+and+return+a+corrected+version+of+the+text' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{
"text": "Ths sentance has som speling mistaeks."
}'
After signing up, every developer is assigned a personal API access key, a unique combination of letters and digits provided to access to our API endpoint. To authenticate with the Text Intelligence API simply include your bearer token in the Authorization header.
| Header | Description |
|---|---|
Authorization
|
Required
Should be Bearer access_key. See "Your API Access Key" above when you are subscribed.
|
No long-term commitment. Upgrade, downgrade, or cancel anytime. Free Trial includes up to 50 requests.
(Save 2 months with annual billing 🎉)
Trusted by leading companies
CPU-based NLP aggregate — sentiment, toxicity, language detection, NER, semantic similarity, and spellcheck.
Each endpoint returns structured JSON data. For example, the sentiment endpoint returns a label (positive/negative) and a confidence score, while the toxicity endpoint indicates whether the text is toxic and provides a score.
Key fields include "label" and "score" for sentiment, "toxic" and "label" for toxicity, "detected" and "probabilities" for language detection, and "similarity" for similarity scores. Each endpoint has specific fields relevant to its function.
Parameters vary by endpoint. For instance, the sentiment endpoint accepts a single text input, while the batch sentiment endpoint accepts an array of texts. The similarity endpoints require two texts or a list of candidates and a query.
Response data is organized in a JSON format with clear key-value pairs. For example, the spellcheck endpoint returns the original text, corrected text, and a dictionary of misspelled words with their corrections.
The API utilizes open-source models trained on various datasets. For example, the toxicity model is trained on Jigsaw data, ensuring a diverse and comprehensive understanding of language nuances.
Typical use cases include sentiment analysis for customer feedback, toxicity detection in user-generated content, language detection for multilingual applications, and spellchecking in text processing tools.
Users can customize requests by selecting specific endpoints and providing relevant text inputs. For batch processing, users can send multiple texts in a single request to optimize performance.
If an endpoint returns partial or empty results, users should check the input data for errors or ensure that the text is not too short. Implementing error handling in the application can help manage such scenarios effectively.
To obtain your API key, first sign in to your account and navigate to the API you want to use. From the API's Pricing section, choose a plan and complete the subscription process. Once subscribed, return to the API page and you will see your API Access Key displayed at the top of the documentation page. You can use this key to authenticate your requests.
You can’t switch APIs during the free trial. If you subscribe to a different API, your trial will end and the new subscription will start as a paid plan.
The free trial lasts for 7 days and allows you to make up to 50 API requests.
No, the free trial is available only once, so we recommend using it on the API that interests you the most. Most of our APIs offer a free trial, but some may not include this option.
Yes. If the API offers a free trial, you will see a "Free 7-Day Trial" option in its Pricing section. The trial lasts for 7 days and allows up to 50 API requests, enabling you to evaluate the API before subscribing to a paid plan.
Zyla API Hub is like a big store for APIs, where you can find thousands of them all in one place. We also offer dedicated support and real-time monitoring of all APIs. Once you sign up, you can pick and choose which APIs you want to use. Just remember, each API needs its own subscription. But if you subscribe to multiple ones, you'll use the same key for all of them, making things easier for you.
You can monitor your API usage through the response headers included with every request:
x-zyla-api-calls-monthly-used: Shows the total number of API requests you have used during the current billing period.
x-zyla-api-calls-monthly-remaining: Shows the number of API requests you have remaining for the current billing period.
Yes, you can cancel your subscription at any time. Simply go to the Pricing section of the API you're subscribed to and click the "Unsubscribe" button.
Please note that upgrades, downgrades, and cancellations take effect immediately. Once your subscription is canceled, access to the service will end immediately, regardless of any remaining API calls in your quota.
Please have a look at our Refund Policy: https://zylalabs.com/terms#refund