Summarization

Summarization provides a brief summary of the audio.

summarize string.

Pre-recorded Streaming:Nova English (all available regions)

Deepgram’s Summarization feature summarizes the content of the submitted audio and returns a brief summary in the JSON response.

Enable Feature

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

summarize=v2

You can also use summarize=true, which will return the V2 response structure.

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

cURL
$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?summarize=v2'

Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

Query Parameters

ParameterValueTypeDescription
summarizev2stringEnables summarization. The output response will include a single object with a result and short summary of the entire audio. It will generate one summary across all channels.
summarizetruebooleanEnables summarization. Returns the same V2 response structure as summarize=v2.
summarizefalsebooleanDisables the summarization feature.

Summarization requires a minimum of greater than 50 words for summarization. For shorter inputs (less than 50 words), the original input will be returned. In this case, no tokens in or out are billed as summarization usage.

Analyze Response

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

JSON
1{
2 "metadata": {...},
3 "results": {
4 "channels": [
5 {
6 "alternatives": [...]
7 }
8 ],
9 "summary": {
10 "result":"success"
11 "short": "Jake calls the Honda dealership and speaks with Josh about the new Honda Civic 2023. Jake schedules a test drive for the hybrid model on Friday and provides his contact information.Josh confirms the appointment and tells Jake to call if he has any further questions."
12 }
13 }
14}

The summary object contains:

  • result: Status of the request (success | failure).
  • short: Short summary of the audio being summarized.

This summarization feature produces one summary across all channels so that the summary field ranks at the same place in the JSON response as the channels array.

API Error and Warning Response

Error

If you request Summarization with an unsupported language by specifying a language code such as summarize=v2&language=es, you will get an error message like the one below.

JSON
1{
2 "err_code": "Bad Request",
3 "err_msg": "Summarization v2 not supported for non-English languages",
4 "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
5}

Warning

If you request Summarization with automatic language detection such as summarize=v2&detect_language=true, where the detected language is unsupported (Spanish, for example), you will get the response, including a transcript and a warning object.

JSON
1"warnings": [
2 {
3 "parameter": "TEXT",
4 "type": "unsupported_language",
5 "message": "TEXT"
6 }
7]
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:

JSON
1{
2 "metadata": {
3...
4 },
5 "warnings": [
6 {
7 "parameter": "summarize",
8 "type": "unsupported_language",
9 "message": "Summarization isn’t supported for the detected language."
10 }
11 ],
12 },
13 "results": {
14 "channels": [
15 {
16 "alternatives": [...]
17 }
18 ],
19 "summary":
20 {
21 "result": "failure",
22 "short": "The summarization feature is currently only available in English. Please check out our API documentation for more details."
23 }
24 }
25}