What changed
Chat Widget now supports EveryCatch’s native Speech-to-Speech (S2S) Voice AI agents alongside existing Voice AI agents.
- S2S and existing Voice AI agents are available within the same Agent dropdown.
- The Chat Widget automatically identifies the selected agent type and launches the appropriate voice experience.
- Existing Voice AI agents continue to work as before, with no changes required to the widget UI or embed code.
- If an existing agent is switched to a supported S2S model, widgets already using that agent update automatically.
- The existing Chat Widget calling experience remains unchanged, including
- Two-way audio
- Mute / unmute
- Call status
- End-call controls
- The S2S SDK is loaded only when a visitor initiates a call with an S2S agent, keeping regular widget loads and existing Voice AI calls unaffected.
How it works
- Enable Speech-to-Speech Voice AI from Labs.
- Create a new S2S agent or switch an existing Voice AI agent to a supported S2S model.
- Navigate to Chat Widget → Agent.
- Select the required Voice AI or S2S agent from the unified dropdown.
- Save the widget.
- The widget automatically launches the correct voice experience when a visitor starts a call.
When an existing agent is switched to an S2S model, widgets already linked to that agent update automatically, no re-save, re-embed, or new agent ID is required.
If a cloned agent is used instead, select the new cloned agent within the Chat Widget builder.
Why it matters
- Agencies can now use EveryCatch’s native S2S Voice AI agents across both phone and website Chat Widget conversations.
- Existing widgets can adopt S2S capabilities without requiring website code changes or widget reconstruction.
- A unified agent picker simplifies configuration by removing the need for separate S2S and Voice AI setup flows.
- Automatic syncing makes it easier to upgrade existing agents to S2S models without manually updating every widget.
- On-demand SDK loading ensures S2S functionality is introduced without impacting standard Chat Widget performance.
Notes
- Availability: Live in production for agencies with Speech-to-Speech Voice AI enabled through Labs.
- Existing Voice AI agents and widgets remain fully compatible.
- Existing embed snippets do not need to be updated.
