Deepgram Post Read Analyze

From 0.36 credits per 1,000 input tokens
ae_deepgram_post_read_analyze

Analyze plain text or an existing transcript with Deepgram Read (POST /v1/read) for sentiment, summaries, topics, and intents. Provide the native OpenAPI 3.1 JSON body through the required request_body object, with a required text string, for example {"request_body":{"text":"Text to analyze"}}. Enable the desired features using sentiment, summarize, topics, and intents; all default to false. Optional custom topics and intents accept strings or string arrays, with strict or extended modes (default extended); up to 100 custom topics are supported. language defaults to en, and tag supports usage-report labels. Returns synchronously and bills the actual input and output tokens of the requested analyses. Successful responses include metadata and results for the requested analyses. This tool analyzes text, not audio.

Productivity
From 0.36 credits per 1,000 input tokens

Pricing

From 0.36 credits per 1,000 input tokens
ModeRate
Input tokens0.36 credits per 1,000 tokens
Output tokens0.72 credits per 1,000 tokens

Billed on the actual input and output token counts reported by Deepgram, summed across enabled analyses.

Round the final total to three decimal places below 1 credit, or two places at 1 credit or more. Positive totals have a 0.001-credit minimum.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
tagstring | arrayNoLabel your requests for the purpose of identification during usage reporting—
topicsbooleanNoDetect topics throughout a transcript or textfalse
intentsbooleanNoRecognizes speaker intent throughout a transcript or textfalse
languagestringNoThe [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are availableen
sentimentbooleanNoRecognizes the sentiment throughout a transcript or textfalse
summarizebooleanNoWhether to summarize the analyzed text.false
custom_topicstring | arrayNoCustom topics you want the model to detect within your input audio or text if present Submit up to `100`.—
request_bodyobjectYesNo parameter description.—
request_body.textstringYesRequired plain text to analyze.—
custom_intentstring | arrayNoCustom intents you want the model to detect within your input audio if present—
custom_topic_modeunknownNoSets how the model will interpret strings submitted to the `custom_topic` param. When `strict`, the model will only return topics submitted using the `custom_topic` param. When `extended`, the model will return its own detected topics in addition to those submitted using the `custom_topic` paramextended
custom_intent_modeunknownNoSets how the model will interpret intents submitted to the `custom_intent` param. When `strict`, the model will only return intents submitted using the `custom_intent` param. When `extended`, the model will return its own detected intents in the `custom_intent` param.extended

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key
Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_deepgram_post_read_analyze' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "text": "Hello. This is a short test."
    },
    "sentiment": true
  }
}'
Response exampleresponse.json
JSONPartial content
{
  "metadata": {
    "created": "2026-11-11T09:50:43.890Z",
    "language": "en",
    "request_id": "01a1ca04-5437-7e72-b142-78231792e62a",
    "sentiment_info": {
      "input_tokens": 9,
      "model_uuid": "80ab3179-d113-4254-bd6b-4a2f96498695",
      "output_tokens": 9
    }
  },
  "results": {
    "sentiments": {
      "average": {
        "sentiment": "neutral",
        "sentiment_score": -0.3003314865960015
      },
      "segments": [
        {
          "end_word": 0,
          "sentiment": "neutral",
          "sentiment_score": 0.018281638622283936,
          "start_word": 0,
          "text": "Hello."
        }
      ]
    }
  }
}

This example shows part of the response. Copied content is valid JSON.