Sentiment Analysis

Sentiment Analysis recognizes the sentiment throughout an entire transcript.

sentiment boolean   Default: false

🛝

Try this feature out in our API Playground!

Deepgram's Sentiment Analysis feature recognizes the sentiment of the entire transcript and detects shifts in sentiment throughout the transcript.

A sentiment of positive, negative, or neutral along with a sentiment_score is identified for each segment of the transcript, and an average of the entire transcript's sentiment is also provided along with the average sentiment_score.

This sentiment feature produces sentiment analysis at every level of transcription requested, so you'll get sentiment values for every word, sentence, utterance, and paragraph, in addition to the top-level sentiment for the entire transcription.

📘

The break point for a sentiment_score becoming positive or negative is +-0.333333333....

Enable Feature

To enable Sentiment, use the following parameter in the query string when you call Deepgram’s /listen endpoint:

sentiment=true

To transcribe audio from a file on your computer, run the following curl command in a terminal or your favorite API client.

curl \
  --request POST \
  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
  --header 'Content-Type: audio/wav' \
  --data-binary @youraudio.wav \
  --url 'https://api.deepgram.com/v1/listen?sentiment=true'

🚧

Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

Query Parameters

ParameterValuesTypeDescription
sentimenttruebooleanEnables sentiment analysis
languageenstringThe language of your input audio (Only English is supported at this time.)

Analyze Response

When the file is finished processing, you’ll receive a JSON response that has the following basic structure:

"metadata": {...},
  "results": {
    "channels": [
      {
        "alternatives": [...]
      }
    ],
    "sentiments": {
      "segments": [
        {
          "text": "Hi there. I love my current phone, but want a new one.",
          "start_word": 0,
          "end_word": 11,
          "sentiment": "positive",
          "sentiment_score": 0.4443286657333374
        },
        {
          "text": "Can I upgrade my phone?",
          "start_word": 12,
          "end_word": 16,
          "sentiment": "neutral",
          "sentiment_score": 0.1317894160747528
        }
      ],
      "average": {
        "sentiment": "positive",
        "sentiment_score": 0.35909067500721326
      }
    }
  }
}

ℹ️

Use the API reference or the API Playground to view the detailed response.

The sentiment values added to objects are:

  • sentiment: The sentiment of the associated text ('positive' | 'negative' | 'neutral').
  • sentiment_score: A floating point value between -1 and 1 representing the sentiment of the associated span of text. -1 being the most negative sentiment, and 1 being the most positive sentiment.

Response Properties

PropertyDescription
channels.alternatives.words[i].sentimentThe sentiment rating and score for the associated word.
sentiments.segmentsSpans of text covering your entire transcript that show when the sentiment shifts throughout the transcribed audio.
sentiments.segments[i].sentimentA rating for the given span of text. Can be either positive, neutral, or negative.
sentiments.segments[i].sentiment_scoreA floating point value between -1 and 1 representing the sentiment of the associated span of text, with -1 being the most negative sentiment, and 1 being the most positive sentiment.
sentiments.averageThe average sentiment for the entire transcription.

API Warning Response

Warning

If you request Sentiment Analysis with an unsupported language by specifying a language code such as sentiment=true&language=es or sentiment=true&detect_language=true where the detected language is unsupported, you will get the warning message below.

"warnings": [
  {
    "parameter": "sentiment",
    "type": "unsupported_language",
    "message": "Sentiment is only supported for English."
  }
]
Warning NameWarning Message
unsupported_languageFeature isn't supported with the specified or detected language.

Example Warning

Here is an example of the JSON structure of a request with warning object.

{
 "metadata": {
...
       },
     "warnings": [
       {
         "parameter": "sentiment",
         "type": "unsupported_language",
         "message": "Sentiment is only supported for English."
       }
     ]
   },
 "results": {
       "channels": [
            {
                "alternatives": [...]
            }
        ], 

    }
}