Realistic Voice simulations: now matching real call behavior

New knowledge articles and Playbooks fields in the Data Export API

The Conversations endpoint in the Data Export API (v2) now exposes two new fields:

used_articles: the knowledge articles referenced during the conversation, each with id, name, url, and source.
used_playbooks: the Playbooks invoked during the conversation, each with id, name, playbook_execution_id, and outcome_status.

Both return an empty array when none applied. For more details, see the conversation object reference.

Voice Simulations now run through the same voice pipeline as live calls, so what you hear in a simulation is what your callers experience in real life.

They now cover behavior that only happens on a real call—speech recognition, natural pacing, and real-world latency—and each result includes a recording of the call alongside the transcript and pass/fail evaluation.

You can also use the Scenario field to shape how the simulated caller behaves and test against realistic conditions:

Tone and emotion (for example, a frustrated or rushed caller)
Accent or dialect
Speaking speed
Keypad (DTMF) input
SMS (send and receive)

To get started, create a test case and select Voice as the channel. Learn more in the Simulations documentation.