The Speech Analytics API Bundle provides a REST API interface to accurately transcribe your meetings, phone calls, and other offline meeting recordings and extract speech and conversation insights using Marsview's proprietary AI and NLP models.
Marsview Automatic Speech Recognition (ASR) technology accurately converts speech into text in live or batch mode. API can be deployed in the cloud or on-premise. Get superior accuracy, speaker separation, punctuation, casing, word-level time markers, and more. (Supported Language: English)
automatically detect the number of speakers in your audio file, and each word in the transcription text can be associated with its speaker
Keywords & Topics
Extract the most relevant topics, concepts, discussion points from the conversation are generated based on each paragraph spoken (Topics by Sentence).
Tone Analysis suggests speaker emotion using only audio clues. Sometimes the speaker may show emotions in the tone of the response and this is important to capture to get the overall sentiment/mood of the conversation which cannot be extracted from conventional Lexical Emotion analysis.
Marsview is capable of detecting the following tone in an audio file:
The Emotion Analysis model will help you understand and interpret speaker emotions in a conversation or text. It is designed to understand human conversation in the form of free text or spoken text and is designed after the emotion wheel.
Marsview is capable of detecting the following Emotions in an audio file:
Sentiment Analysis will help you interpret and quantify if the conversation in the audio or text is Positive, Negative, or Neutral.
Speech/Conversation Type Detection
Speech Type model helps you understand the type of conversation at any given time. Every phone call, online or offline conversation can be broadly classified into four categories - Statement, Command, Action Item, or a Question.
Action Items Detection
Action Item API detects an event, task, activity, or action that needs to take place in the future (after the conversation). These Action items can be of high priority with a definite assignee and due date or of lower priority with a non-definite due date.
All action items are generated with action phrases, assignees, and due dates to make the output immediately consumable by your CRM or project management tools
Questions & Responses Detection
Automatically identify and detect questions or requests posed during the conversation and also the apt response in the conversation in a consumable form. The API detects the Question and Response by the speaker.
Extractive summarization aims at identifying the salient information that is then extracted and grouped together to form a concise summary.
Screengrabs (Chapter Detection)
Captures keyframes and slides from videos and screen sharing from an online web conference.
Identify and analyze the visual aspects of the meeting along with the corresponding timestamps and with Screen Activity API.
Marsview detects the following Screen Activity:
For easy testing using Postman, we provided a Postman Collection for Marsview Speech Analytics APIs. This is a simple 6 step tutorial to quickly test out the Marsview Speech & Conversation Analytics APIs.
The files are available here:
After downloading Postman and Marsview's Postman Collection. You can
File > import the collection into Postman to get started.
Get your API Key and API Secret by registering to Marsview as a developer.
Set a New Environment on Postman as shown below, this will ensure all the variables that will be set in further steps in the process are correctly assigned.
Click on the
More > Edit
Variables tab set
apiSecret as Workspace variables on Postman as shown below.
Using the API
[POST] Get token API you will be able to generate an
accessTokenthat will expire in 1 hour from the time of token generation. You will be able to upload an audio/video file or a file URL using this
Instruction: Click on
Get token and click on
You can upload an Audio/Video File using
[POST] Upload file or use
[POST] Upload file url (Recommended) to submit/upload a file URL.
Instruction: Fill in the file details such as
link(URL) and click on
This will generate a Transaction ID or
txnIdwhich is a unique ID generated for a particular file or URL submitted to Marsview.
Each AI model/API (mentioned in the Overview section) can be configured to get the most accurate results for your use case. To know more about the configurations go to Speech & Conversation API Overview.
Instruction: For ease of testing, we have preconfigured all the API to default configuration values so all you have to do is go to
[POST] Upload request and hit
You will see an output JSON as shown below with the status
[GET] Request Status is used to get the status of the file being processed. The status will go from
"completed". If there's an error transcribing your file, the status will go to
"error" and there will be an
"msg" key in the response JSON which will contain more information.
Once the Request Status is set to
"completed", you'll see a full JSON response with your transcription text, like this by sending a request to the
Instruction: Click on
[GET]Metadata and click on
Our support team is available to respond to user requests via email at [email protected]
1st Response SLA is less than 24 hours.
Users must reach us by filling out the support form available here with their Full Name, Email Address and a brief description of the problem.
A support engineer shall respond with 2 hours with a support case number.
You can also Book a Call with our engineers.