Cross-channel support
Conversation Intelligence supports multiple Twilio communication channels and reasons across channels through a single Conversation object.
Conversation Intelligence integrates with Conversation Orchestrator. Conversations represent communications between multiple participants that occur across one or more Twilio channels.
Conversation Orchestrator ingests and normalizes these communications into a Conversation and can automatically activate your intelligence configurations.
Direct ingestion not supported
Conversation Intelligence doesn't support direct ingestion of raw Twilio channel events. All channel data must flow through Conversation Orchestrator.
| Channel | Status |
|---|---|
| Voice - Call | ✅ Available |
| Messaging - SMS | ✅ Available |
| Messaging - RCS | ✅ Available |
| Messaging - WhatsApp | ✅ Available |
| Chat | ✅ Available |
| Voice - Recording | ✅ Available (Public Beta) |
| Video | ⏳ Not yet available |
| ⏳ Not yet available | |
| Voice - Conference | ⏳ Not yet available |
Chained configuration allows you to automate the workflow from audio capture to AI-driven insights. By linking specific API resources, you can eliminate manual handoffs and automatically trigger Conversation Orchestrator and Conversation Intelligence workflows for both batch and real-time transcription.
Batch transcription workflow not supported in Conversation Intelligence (classic)
The Transcription Configuration resource for batch transcription (public beta) isn't available for customers using Conversation Intelligence (classic). To use it with the latest version of Conversation Intelligence, contact Support or your Twilio account team.
Twilio's Voice Configuration API supports the Recording Configuration resource for managing call recording settings. Within a recording configuration, you can specify a Transcription Configurations resource (public beta) to configure transcription. Once linked, transcription triggers automatically after each recording is captured.
To integrate generated transcriptions with Conversation Orchestrator and Conversation Intelligence, you can optionally pass a conversationConfigurationId as an input parameter in the Transcription Configurations resource. This automatically activates Conversation Orchestrator and Conversation Intelligence rules when the transcript is ready.
Note: For batch transcriptions, you must use the "on conversation end" trigger in your rules to ensure proper processing. Learn more about triggers.
You can pass real-time transcription data to Conversation Orchestrator and Conversation Intelligence by referencing conversationConfigurationId or conversationId as optional parameters in the Real-Time Transcription resource or TwiML.