Home
APIs
Text & Language
Real-Time Multilingual Sentiment Analysis API

Text & Language API

Real-Time Multilingual Sentiment Analysis API

Aspect-based sentiment classification and emotion intensity scoring across 50+ languages.

POST https://rsflowhub.com/api/v1/ai/sentiment-analysis

1 credit per call
First 1,000 calls free every month
X-API-Key header
JSON in, JSON out

Try it in the playground API reference

POST /api/v1/ai/sentiment-analysis

{
    "text": "The dashboard is incredibly fast, but the new billing page is very confusing.",
    "aspects": [
        "dashboard",
        "billing"
    ]
}

200 OK response.json

{
    "result": {
        "sentiment": "mixed",
        "confidence": 0.91,
        "aspect_sentiments": [
            {
                "aspect": "dashboard",
                "sentiment": "positive",
                "confidence": 0.94
            },
            {
                "aspect": "billing",
                "sentiment": "negative",
                "confidence": 0.89
            }
        ]
    }
}

Definition

What is the Real-Time Multilingual Sentiment Analysis API?

Real-Time Multilingual Sentiment Analysis API is a REST API on RSFlowHub for web, mobile and AI agent applications. Send a JSON request to POST /api/v1/ai/sentiment-analysis with your API key; RSFlowHub runs it on a tuned AI model, falls back to a backup provider if needed, and returns a structured JSON result, usually within 1 to 3 seconds.

Tutorial: Sentiment Analysis in Laravel: Step-by-Step Tutorial with a REST API

Try it without code or signup: Free sentiment analyzer

Category: Text & Language
Endpoint: POST /api/v1/ai/sentiment-analysis
Authentication: X-API-Key header
Price: 1 credit per call, first 1,000 free / month
Rate limit: 10 to 120 requests / minute by plan
Typical response: 1 to 3 seconds
Format: JSON, UTF-8

Request parameters

Send these fields as a JSON body. An invalid or missing field returns a 422 error that names the field.

Field	Type	Required	Description
`text`	string	Required	The text content you want to analyze (Max: 5,000 characters).
`aspects`	array of strings	Optional	Optional list of specific topics to analyze sentiment for (e.g., ["UI", "billing", "speed"]). Max 10 items.

Code examples

Copy, replace rfh_your_api_key with your key and run. Prefer a client library? See the official SDKs.

request.sh

curl -X POST "https://rsflowhub.com/api/v1/ai/sentiment-analysis" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: rfh_your_api_key" \
  -d '{"text":"The dashboard is incredibly fast, but the new billing page is very confusing.","aspects":["dashboard","billing"]}'

client.php

<?php

$client = new \GuzzleHttp\Client();
$response = $client->post('https://rsflowhub.com/api/v1/ai/sentiment-analysis', [
    'headers' => [
        'Content-Type' => 'application/json',
        'X-API-Key'    => 'rfh_your_api_key',
    ],
    'json' => array (
      'text' => 'The dashboard is incredibly fast, but the new billing page is very confusing.',
      'aspects' => 
      array (
        0 => 'dashboard',
        1 => 'billing',
      ),
    ),
]);

echo $response->getBody();

client.js

const response = await fetch('https://rsflowhub.com/api/v1/ai/sentiment-analysis', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': 'rfh_your_api_key'
  },
  body: JSON.stringify({"text":"The dashboard is incredibly fast, but the new billing page is very confusing.","aspects":["dashboard","billing"]})
});

const data = await response.json();
console.log(data);

main.py

import requests

url = "https://rsflowhub.com/api/v1/ai/sentiment-analysis"
headers = {
    "Content-Type": "application/json",
    "X-API-Key": "rfh_your_api_key"
}
payload = {"text":"The dashboard is incredibly fast, but the new billing page is very confusing.","aspects":["dashboard","billing"]}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Response

Every RSFlowHub endpoint uses the same envelope, so one parser handles all of them. Failed calls are not charged.

response.json

{
    "success": true,
    "request_id": "req_3f9a2c7e-5b1d-4e8a-9c2f-7d6e1a0b4c8d",
    "data": {
        "result": {
            "sentiment": "mixed",
            "confidence": 0.91,
            "aspect_sentiments": [
                {
                    "aspect": "dashboard",
                    "sentiment": "positive",
                    "confidence": 0.94
                },
                {
                    "aspect": "billing",
                    "sentiment": "negative",
                    "confidence": 0.89
                }
            ]
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

error.json

{
    "success": false,
    "request_id": "req_8c1d4e2a-7f3b-4a9c",
    "error": {
        "code": "VALIDATION_ERROR",
        "message": "The given data was invalid.",
        "details": {
            "text": [
                "This field is required."
            ]
        }
    },
    "meta": {
        "version": "v1",
        "timestamp": "2026-10-05T09:30:00Z"
    }
}

Envelope fields
Field	Type	Meaning
`success`	boolean	true when the call worked, false on any error.
`request_id`	string	Unique id for this call. Quote it when you contact support.
`data.result`	object	The result of this endpoint (see the example).
`error`	object	Only on failure: code, message and details per field.
`meta`	object	API version and server timestamp.

All error codes: Errors reference

Features

Aspect-Based Sentiment Analysis

Analyze sentiment for specific features or subjects (e.g. "pricing", "speed", "support") within a single text block.

Intensity & Emotion Scoring

Returns confidence scores (-1.0 to +1.0) for positive, negative, neutral, and mixed emotional tones.

50+ Languages Supported

Multilingual sentiment classification across English, Spanish, French, German, Hindi, Gujarati, Japanese, and more.

High-Throughput Gateway

Fast enough for live moderation flows and batch analytics jobs.

Use cases

How teams use the Real-Time Multilingual Sentiment Analysis API in production.

E-Commerce & SaaS

Customer Review & NPS Monitoring

Categorize incoming customer reviews and Net Promoter Score (NPS) comments into positive and negative themes.

Input: The dashboard UI is super fast, but customer support took 3 days to reply.
Output: {"overall": "mixed", "aspects": {"dashboard": "positive", "support": "negative"}}

Identifies product pain points in real-time.

Marketing & PR

Social Media Brand Sentiment Tracking

Monitor public social media posts and brand mentions during new feature or product launches.

Input: Just tried the new RSFlowHub API dashboard! Incredible speed and UX!
Output: {"overall": "positive", "confidence": 0.98, "label": "POS"}}

Provides instant feedback on brand perception.

Helpdesk SaaS

Support Ticket Priority Escalation

Auto-flag angry or highly negative support tickets for priority routing to senior agents.

Input: I am extremely frustrated! My account has been locked for 5 hours!
Output: {"overall": "negative", "urgency": "high", "label": "NEG"}}

Reduces customer churn by resolving upset clients first.

AI chatbot

Sentiment analysis for your AI chatbot

An upset visitor should not be left talking to a bot. Run each chat message through the sentiment API and the chatbot can notice frustration early, change its tone, or offer to hand the conversation to your team.

How it works in a chatbot

Visitor: "this is the third time my order is late, I am done with this"
API returns: sentiment "negative", confidence 0.96
Chatbot apologises and offers to open a support ticket

Escalate at the right moment

Offer a human, or create a ticket, as soon as sentiment turns negative.

Measure chatbot quality

Track how often conversations end positive or negative to see which answers need work.

Per-topic sentiment

Pass aspects such as "delivery" or "support" to see what the visitor is unhappy about.

Want a chatbot without building one? The RSFlowHub AI chatbot for your website is live in about 5 minutes with one script tag: it answers from your documents, captures leads and creates support tickets. Read the chat widget guide, try the live chatbot demo, see chatbot pricing, or build your own with the chatbots API.

Real-Time Multilingual Sentiment Analysis API vs building it yourself

The same job done three ways.

Topic	RSFlowHub API	Raw LLM prompts	Rules / regex
Output	Validated JSON fields	Free text you have to parse	Fixed patterns only
Setup	One POST request, no prompts	Write and maintain prompts and parsing	Write and maintain rule lists
Provider outage	Automatic fallback to a backup model	You build retries and a second vendor	Not applicable
Pricing	1 credit per call, failed calls free	Per token, per vendor	Your own servers and upkeep
Understands context	Yes, AI model	Yes, AI model	No, keywords only

Frequently asked questions

Which sentiment classifications does the API return?

The API returns overall sentiment ("positive", "negative", "neutral", "mixed"), numeric confidence scores (-1.0 to +1.0), and optional aspect-level breakdowns.

What is Aspect-Based Sentiment Analysis?

Aspect-Based Sentiment allows you to evaluate sentiment for individual topics inside one comment (e.g. rating "speed" positive while rating "support" negative).

How fast is the Sentiment Analysis API?

Sentiment Analysis requests usually complete in 1 to 3 seconds, depending on input length and the AI model. Identical repeat requests are served from cache and return faster.

Does it support languages other than English?

Yes! The Sentiment Analysis API natively supports over 50 languages with automatic language detection.

How many credits does each request consume?

Standard Sentiment Analysis API requests consume 1 base credit per call.

Start using the Real-Time Multilingual Sentiment Analysis API

Free plan with 100 credits/month + 1,000 bonus credits when you sign in before 23 Nov. Test it in the playground first, no code needed.

Get a free API key Try it now