Declare an Audio Interaction
The first step in processing any interaction is to declare the interaction.
When the POST request successfully executes, an HTTP status is returned to indicate the request was successful, along with a JSON response containing the interactionIdentifier.
It is important you store the interactionIdentifier as it will serve as a required parameter for all other ElevateAI endpoints, enabling you to POST, GET, and/or DELETE information associated with this interaction.
If an error occurs when requesting to declare the interaction, a standard HTTP response code is retuned to indicate the request was unsuccessful, along with a JSON response containing additional details to assist in troubleshooting.
All interactions successfully declared will count towards your monthly request quota, irrespective of file upload status or processing outcome.
Only interactions successfully processed are eligible for billing. Once declared, you can confirm the processing status of the interaction as well as track impacts to usage and spend.
Echo
Introducing Echo, our most accurate transcription model ever!
Echo delivers a significant leap in accuracy, outperforming our previous CX-focused model by 40%, ensuring superior transcription quality across every use case.
To take advantage of the Echo model, add the body parameter "model" to your POST declare and set the value to "echo".
NOTE: Currently the Echo model does not diarize between speakers, perform redaction or process for CX-AI. Future releases will move Echo towards feature parity with the CX model.
Details on transcription and CX AI features supported by language can be found on the overview page.
Providing access to audio files via the downloadUri parameter is highly recommended for fastest processing times.
We take data security seriously, and know you do to! If required, we are able to provide an IP address to support IP whitelisting or assist in setting up a private, secure SFTP to support transferring via SFTP with URL format. If you have any questions on how to transfer your audio, reach out at any time to [email protected] - we're here to help
If the downloadUri parameter is not included when declaring the interaction, the audio should be uploaded to the API directly for processing.
Metadata must only be submitted with an API-Token for an account which has Explore enabled. Use under other circumstances will cause the Declare to fail, and a response of 400 Bad Request.
For details on the types and formatting of metadata, please see Metadata.