---
title: "Insights"
description: "What Speak AI extracts from every recording, what each insight type means, and how to read them without opening the transcript."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.speakai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Insights

Every recording is analyzed the moment it's transcribed: keywords, sentiment, entities, and
topics extracted automatically, no prompt required. Read one file's insights on its page, tune the
[categories](/help/insights/categories/) to your domain, set [keyword alerts](/help/insights/keywords/)
for the phrases that matter, define [AI fields](/help/insights/fields/) for structured extraction,
and use [Explore](/help/insights/explore/) to compare it all across your library, where
[themes](/help/insights/themes/) show what recurs and what's changing.

- **[AI fields](/help/insights/fields/)**
- **[Categories](/help/insights/categories/)**
- **[Explore](/help/insights/explore/)**
- **[Keywords](/help/insights/keywords/)**
- **[Sentiment scores](/help/insights/sentiment/)**
- **[Themes](/help/insights/themes/)**

## Understanding AI insights: keywords, sentiment, and more

## What are insights?

Every time Speak AI transcribes and analyzes your media, it automatically extracts a rich set of insights. These help you understand your content without reading the entire transcript.

## Insight types

### Keywords and topics

The most frequently mentioned terms and topics in your recording. These help you quickly understand what the conversation was about.

### Sentiment analysis

Speak analyzes the emotional tone of your content at both the document level and individual sentence level:

- **Positive:** Optimistic, supportive, or enthusiastic language
- **Negative:** Critical, frustrated, or concerning language
- **Neutral:** Factual, informational statements
- **Compound score:** An overall sentiment score from -1 (most negative) to +1 (most positive)

### Named entities

Speak identifies and categorizes specific entities mentioned in your content:

- **People:** Names of individuals mentioned
- **Organizations:** Companies, institutions, brands
- **Locations:** Cities, countries, addresses
- **Products:** Product and brand names
- **Dates and times:** Specific dates, deadlines, time references
- **Money:** Dollar amounts, pricing, financial figures

### Speaker analytics

For recordings with multiple speakers, Speak tracks:

- **Speaking time:** How long each person spoke
- **Word count:** Total words per speaker
- **Words per minute:** Speaking pace for each person
- **Speaking percentage:** Share of the conversation

### Categories

Speak automatically categorizes your content into relevant topics. You can also create custom categories to match your specific needs (e.g., "Product Feedback", "Action Items", "Customer Complaints").

## Viewing insights

Insights appear in multiple places:

- **Media detail page:** Full insight breakdown for each file
- **Folder statistics:** Aggregate insights across all files in a folder
- **Explore page:** Cross-media analytics and trend analysis
- **AI Chat:** Ask questions about insights ("What were the most negative moments?")

## Custom categories

Create your own insight categories:

1. Go to your [account settings](https://app.speakai.co/profile/usage)
1. Find **Custom Categories**
1. Add your categories and define what they mean
1. New media will be analyzed against your custom categories

You can also generate category suggestions using AI based on your existing content.

For advanced filtering across insights, check out our [Advanced Data Filtering guide](/help/insights/explore/).

## AI features for analyzing qualitative data

## AI Insights Suite

### Overview

Speak AI provides powerful Natural Language Processing (NLP) tools designed to transform your vast amounts of unstructured data into clear, actionable insights. Stop drowning in raw text and start understanding what truly matters.

These features help you quickly identify key information, understand customer sentiment, and discover emerging trends without manual analysis. Unlock the hidden value within your datasets to make better, data-driven decisions.

### How It Works

The AI Insights Suite offers a range of tools to analyze your data:

- **Named Entity Recognition (NER):** Automatically finds and labels important entities like company names, people, locations, and products within your text.
- **Sentiment Analysis:** Assigns a sentiment score (from Positive to Negative) to each sentence, allowing you to track customer feelings and satisfaction trends across thousands of interactions.
- **AI Chat:** This advanced generative AI tool lets you ask specific questions about your data, such as "What are the top 3 feature requests?". The AI will read through all your transcripts to provide a consolidated, summarized answer.
- **Word Clouds:** Visually represents the most frequently used keywords, making it easy to spot and understand emerging themes at a glance.

### Getting Started

To access these features, go to **Speak AI Tools** in your dashboard.

### Use Cases

You can chain these features together for deeper analysis. For example, use NER to filter your data for mentions of a specific competitor, and then apply Sentiment Analysis to understand how customers feel about them.

### Related Prompts/Features

- AI Chat
- Folder Analytics

### Next Steps

Ready to unlock the power of your data? Here's what to do next:

- **Login to your account** and navigate to the **Speak AI Tools** section.
- **Upload your data** if you haven't already.
- **Experiment with the features** like NER and Sentiment Analysis to see what insights you can uncover.
- **Try a AI Chat** to get quick answers to your most pressing questions.

Need help? Contact our support team or check out our other guides.

Analyzing a real dataset? [Book a demo and see your own recordings analyzed](https://calendly.com/speak-ai/demo?utm_source=docs&utm_campaign=book-demo).

Source: https://docs.speakai.co/help/insights/index.mdx
