We are excited to announce our latest Speech Understanding feature – Summarization (summarize=true). Deepgram’s speech recognition API, with Summarization, can auto-generate meaningful summaries from the audio data.

Summarization API endpoint can be called using (summarize=true) and will return summaries block in the response body of the output. Each segment of the summary will have summarized text, start_word, and end_word.

Examples of use cases for Summarization include:

  • Automatically generate call notes and meeting summaries to reduce manual effort.

  • Navigate through a large number of calls and analyze important conversations through generated summaries.

  • Help listeners identify interesting conversations through auto-generated meaningful podcast previews.

The URL query might look like this to call the Summarization API. 


Please see the features page in our documentation to learn more about Summarization.

Please get in touch with us through your dedicated support channel. We’d love to have your feedback, please share it with us at Product Feedback.

Stop building work-arounds for STT systems that don't work.

Start FreeTalk to an expert