Overview

Supercharge your conversation with Marsview's Conversation API Bundle powered by the Conversation Intelligence Platform.

The Conversation API Bundle provides a REST API interface to accurately transcribe your meetings, phone calls, chat messages, emails, and offline meeting recordings.

Additionally, the Conversation API can extract actionable insights from your conversations as listed below:

Features

Short Description

Speech-to-text

accurately converts speech into text in live or batch mode

Speaker Separation

automatically detect the number of speakers in your audio file, and each word in the transcription text can be associated with its speaker

Tone Analysis

Understanding the emotion of the speaker by the tone of their voice

Emotion Analysis

Analyze speaker emotions based on spoken text (Lexical Emotion Analysis)

Sentiment Analysis

Analyze speaker sentiment based on spoken text (Lexical Emotion Analysis)

Speech Type

Distinguish between speech type and capture actionable notes during your conversation

Audio Classification

This API allows you to distinguish audio sounds to one of the 500+ classes available

Action Items

This API returns a list of all the action items generated from the conversation

Question & Response

This API returns a list of all the questions and responses from the conversation

Topics

This API helps you detect topics, entities, concepts, keywords, and key-phrases from the conversation.

Abstractive Summary

This API will summarize your conversation using the building of new information based on the conversation.

Extractive Summary

This API will summarize your conversation using the salient information present in the conversation.

Conversation Insights

This API provides you with useful conversational insights that can measure or help measure many of your KPIs.

Screengrabs (visual)

This API captures keyframes and slides from a visual meeting/conversation.

Screen Activity (visual)

This API captures the visual activity in a conversation

OCR

This API converts typed, handwritten, or printed text into machine-encoded text

Supported Input types: Audio, Video