Create Audio Intelligence

Analyzes an audio file and provides comprehensive insights.

HTTP Request

POST https://app.resemble.ai/api/v2/audio_intelligence

Request Body

Parameter	Type	Description
url	string	URL of the audio file to analyze
json	boolean	(Optional) If true, returns a structured JSON response

Response

If json is not set or false, returns an AudioIntelligenceResponse object with a description string.

If json is set to true, returns an AudioIntelligenceJSONResponse object with structured data.

Response Fields

Field	Type	Description
success	boolean	Indicates whether the operation was successful
item	object	Contains the analysis results
description	string or object	Analysis results as a string or structured object
created_at	string	Timestamp of when the analysis was created

When json is true, the description field contains the following structured data:

Field	Type	Description
speaker_info	string	Information about the speaker's characteristics
language	string	Detected language of the audio
dialect	string	Detected dialect or accent
emotion	string	Detected emotion in the speech
speaking_style	string	Analysis of the speaking style
context	string	Contextual information about the audio content
message	string	Main message or purpose of the audio content
transcription	string	Full transcription of the audio
translation	string or null	Translation of the content (if applicable)

Example

curl --request POST \
  --url https://app.resemble.ai/api/v2/audio_intelligence \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-type: application/json' \
  --data '{
  "url": "https://example.com/audio/sample.wav",
  "json": true
}'

Replace YOUR_API_KEY with your actual Resemble AI API key.

Authentication

All API requests require authentication using a bearer token in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Ensure that you provide a valid URL and that the audio file is in a supported format.