Extract the most relevant topics, concepts, discussion points from the conversation are generated based on the overall scope of the discussion (Global Topics) or by each paragraph spoken (Topics by Sentence).
Input Type Supported: Audio, Text
Model Dependency: Speech to Text, Speaker Separation
Type | Description |
AI-generated topics | Topics generated by AI based on key concepts spoken, topics modeling. |
Entity | Extract entities such as custom, location, person, date, number, organization, date-time, date range, etc. from the conversation. |
Tech Topics | Extract Technology terms from the conversation |
Finance Topics | Extract Financial terms from the conversation |
Medical Topics | Extract Medical/Pharma terms from the conversation |
Custom Topics | Contact us for more info: [email protected] |
Transaction ID is returned in the JSON body once the processing job is launched successfully.
This Transaction ID can be used to check the status of the job or fetch the results of the job once the metadata is computed{"status":true,"transaction_id":32dcef1a-5724-4df8-a4a5-fb43c047716b,"message": " Compute job for file-id: 32dcef1a-5724-4df8-a4a5-fb43c047716b launched successfully"}
Speech to Text has to be enabled for Action Items to be enabled){"status":false,"error":{"code":"MCST07","message":"DependencyError: emotion_analysis depends on speech_to_text"}}
curl --request POST 'https://api.marsview.ai/v1/conversation/compute' \--header 'appSecret: 32dcef1a-5724-4df8-a4a5-fb43c047716b' \--header 'appId: 1ZrKT0tTv7rVWX-qNAKLc' \--header 'Content-Type: application/json' \--data-raw '{"settings":{"speech_to_text":{"enable":true,"pii_detection":false,"custom_vocabulary":["Marsview" , "Pikachu"],"topics":true},"speaker_separation":{"enable":true,"num_speakers":4},"speech_type_analysis":{"enable":true},"topics":{"global_enable":true}}}'
Given below is a sample response JSON when the Status code is 200.
{"status":true,"transaction_id":32dcef1a-5724-4df8-a4a5-fb43c047716b,"message": " Compute job for file-id: 32dcef1a-5724-4df8-a4a5-fb43c047716b launched successfully"}
The most relevant topics, concepts, discussion points from the conversation are generated based on the overall scope of the discussion.
data object returns the requested metadata if it is computed. The status object shows the current state of the requested metadata. Status for each metadata field can take values "Queued"/"Processing"/"Completed".
Shown below is a case where "global_topics" Job is in "Queued" state and "Completed" state. {"status":{"global_topics":"Queued",}"data":{"global_topics":{}}}
{"status":{"global_topics":"Completed"}"data":{"global_topics":[...{"topic":"Machine Learning","type": "AI Generated"},{"topic":"Tesla","type": "Entity-Name"},{"topic":"sales forecast","type":"Finance"},...]}}
Fields | Description |
| List of global topics extracted from the audio/video file |
| Text of the extracted topic |
| Type of the extracted topic |
The most relevant topics, concepts, discussion points from the conversation are generated based on each sentence/paragraph spoken.
Sentence level topics are generated as a part of the Speech To Text object.