Data ingestion methods

Bring data into Medallia Speech for ingestion and processing.

To use Medallia Speech, you must first upload audio, video, or completed JSON transcripts to a centralized storage location, then initiate file ingestion and processing by the Speech pipeline.

Medallia Speech supports two ways of ingesting records for processing:

  • Connectors
  • Speech API

After ingesting records, the Speech pipeline calculates and maps Experience Cloud fields and metrics, sends transcripts to Text Analytics, and makes the resulting data available in Reporting. This complete pipeline begins with raw audio and ends with actionable insights for your team.

The sections below describe each ingestion method and their unique benefits.

Connectors

A connector is an out-of-the-box, pre-built integration to bring signals, including audio data, into Experience Cloud.

Note: Connectors do not support ingesting transcripts at this time.

Benefits of using connectors

Connectors are best for organizations that do not wish to develop custom code to initiate file ingestion and processing, especially those who use specific contact center platforms.

In addition to the pre-built contact center connectors, you can also use connectors to pull data from an S3 bucket or SFTP server.

Connectors allow you to:

  • Ingest files without the need for custom code or application development. All configuration is done in the Experience Cloud UI.

  • Use a pre-built solution for your specific contact center platform.

  • Simplify the process by staging files in an S3 bucket or SFTP server.

To learn more about this ingestion method, see Connectors.

Speech API

When using the Speech API, you can upload raw audio or video files to be transcribed by Speech, or you can upload complete transcripts that were created by your own Automatic Speech Recognition (ASR) engine.

Benefits of using the Speech API

The Speech API is best when you wish to use your own custom code and applications to initiate file ingestion and processing. The API allows you to:

  • Interact with the Speech API from your own custom applications.

  • Upload completed JSON transcripts that were created with your own Automatic Speech Recognition (ASR) engine rather than choosing one of Medallia's engines.

To view developer documentation, see Speech API.