Amazon Transcribe Call Analytics now offers generative call summarization (preview)

We are excited to announce the preview of generative AI-powered call summarization in Amazon Transcribe Call Analytics to boost contact center agent and manager productivity, and improve customer experience. Powered by Amazon Bedrock, generative call summarization delivers a concise summary of a contact center interaction that captures key components such as why the customer called, how the issue was addressed, and what follow-up actions were identified.

Contact center agents spend precious time after each call manually summarizing the notes. Managers also spend significant time listening to call recordings or reading entire transcripts while investigating caller issues. With generative call summarization, Amazon Transcribe Call Analytics can now automatically condense the entire call recording into a concise summary. For example, this is a sample summary of a 10-minute call: “Customer reported a missing order even after 10 days from expected delivery date. The agent offered a free replacement and $10 credit. The agent will follow-up with the customer in 2 days to confirm the receipt of the replacement order”. Agents can now spend more time talking to callers waiting in queue rather than engaging in after-call work, thus improving customer experience. Managers can quickly understand the context of an interaction without reading the whole transcript.

The generative call summarization capability is currently supported in English language and is available in the following AWS regions: US East (N. Virginia) and US West (Oregon).

To learn more, visit the blog post and documentation. For details on pricing, please refer to the pricing page.