Audio-Emotion-Recognition

Emotion recognition api extract basic emotions, intensity, & sentiment from the audio file. It can be used with DeepAffects Speaker Identification API.

POST Request

POST https://proxy.api.deepaffects.com/audio/generic/api/v2/sync/recognise_emotion

POST https://proxy.api.deepaffects.com/audio/generic/api/v2/async/recognise_emotion

Sample Code

Shell

curl -X POST "https://proxy.api.deepaffects.com/audio/generic/api/v2/sync/recognise_emotion?apikey=<API_KEY>" -H 'content-type: application/json' -d @data.json

curl -X POST "https://proxy.api.deepaffects.com/audio/generic/api/v2/async/recognise_emotion?apikey=<API_KEY>&webhook=<Your webhook url>&request_id=abcd-1234" -H 'content-type: application/json' -d @data.json

# contents of data.json
{"content": "bytesEncodedAudioString", "sampleRate": 8000, "encoding": "FLAC", "languageCode": "en-US"}

Output

# Sync:

{
    "segments":
        [{
        "emotion": "joy",
        "start": 0,
        "end": 1
    }]
}

# Async:

{
"request_id": "8bdd983a-c6bd-4159-982d-6a2471406d62",
"api": "requested_api_name"
}

# Webhook:

{
"request_id": "8bdd983a-c6bd-4159-982d-6a2471406d62",
"response": {
    "segments":
        [{
        "emotion": "joy",
        "start": 0,
        "end": 1
    }]
}
}

Body Parameters

Parameter	Type	Description	Notes
encoding	String	Encoding of audio file like MP3, WAV etc.
sampleRate	Number	Sample rate of the audio file.
languageCode	String	Language spoken in the audio file.	[default to 'en-US']
content	String	base64 encoding of the audio file.

Query Parameters

Parameter	Type	Description	Notes
api_key	String	The apikey	Required for authentication inside all requests
webhook	String	The webhook url at which the responses will be sent	Required for async requests
request_id	Number	An optional unique id to link async response with the original request	Optional

Output Parameters

Output is the list of emotion scores. The parameters in emotion scores are as follows:

Parameter	Type	Description	Notes
emotion	String	Type of emotion like Happy, Sad, Surprised etc.
start	Float	Start of the audio segment.
end	Float	end of the audio segment.

Output Parameters (Async)

Parameter	Type	Description	Notes
request_id	String	The request id	This defaults to the originally sent id or is generated by the api
api	String	The api method which was called

Output Parameters (Webhook)

Parameter	Type	Description	Notes
request_id	String	The request id	This defaults to the originally sent id or is generated by the api
response	Object	Response object same as sync api response.

About

DeepAffects is a speech analysis platform for Developers. We offer a number of speech analysis apis like, Speech Enhancement, Multi-Speaker Diarization, Emotion Recognition, Voice-prints, Conversation Metrics etc. For more information, checkout our developer portal