We’re rolled out the Session Continuation feature, designed to make interactions with your agents more cohesive and context-aware:

: Pass a when starting a new call to allow the agent to reference and continue from where the previous session left off. Learn more here: Session Continuation

: The agent can now recall relevant details from past interactions, enabling smoother and more personalized conversations.

: We’re working on additional options to identify users through user_id, phone number, or similar identifiers to make session memory even more intuitive.

: A new centralized page aggregates all your call histories in one place for easier tracking and analysis.

: You can now set a response delay for agents. While we’ve optimized latency for fast responses, this option allows you to add a natural pause before the agent replies, enhancing conversational flow.

: Easily pass metadata to your embedding widget by adding parameters to the embedding URL. Learn more here: Adding Metadata via URL Parameters.

We’re excited to announce the launch of App Functions, starting with an integration for Cal.com, designed to simplify common use cases like booking appointments on a calendar:

: Easily enable agents to handle scheduling tasks. Just provide your API key and Event Type ID, and your agent will handle the rest—no further configuration needed.

: You can now set the agent’s timezone in the configuration, a required setting for appointment booking features to work accurately.

This feature streamlines workflows and makes it easier to connect your agents to external tools for enhanced productivity and user experience.

: You can now enable call recording for all your calls. Recordings are stored securely, and a recording_url is included in the End-of-Call Webhook, allowing you to access and manage recordings easily for training, or analysis.

: Agents can now handle voicemails seamlessly with configurable options:

: Enhance call management with the ability to transfer calls to another agent or external phone number. You can specify the transfer target dynamically, ensuring smooth handoffs for complex workflows or escalations.

These features make it easier to manage call workflows and enhance the overall experience for both users and agents.

We’re added the Dynamic Variables feature, which allows you to create highly customizable and personalized agent interactions:

: Dynamic variables are automatically created from metadata you pass into the system. All metadata fields become accessible as variables. Additionally, there are default variables like FromPhone and ToPhone for phone-related data.

: Variables can be used across prompts, agent messages, and even passed as parameters in function calls, enabling dynamic and context-aware responses.

: Explore how to use dynamic variables in our documentation: Dynamic Variables.

This feature unlocks endless possibilities for creating smarter and more personalized agent interactions!

: We’ve added support for running outbound campaigns at scale. Upload your contact list (CSV or manual), add extra details like names, and start your campaign with a single click. Millis takes care of scheduling and scaling the calls for you. Check call statuses in real-time from the dashboard to stay on top of your campaign's progress. Check it out here

: We’ve added APIs for managing outbound campaigns and phone numbers. These make it easy to integrate Millis into your existing systems and automate your workflows.

We’re excited to announce that Millis AI has integrated with OpenAI’s latest speech model, the Realtime API! This cutting-edge model allows for natural, low-latency conversations that you can use directly from Millis platform without needing to modify any existing code on your end.

You’ll continue to enjoy all the other benefits of the Millis ecosystem, such as telephony integration, webhook automation, and more.

Based on our evaluation, the model is still in its alpha phase and isn’t quite ready for production use, but we encourage you to test it out! You can access it directly through both the dashboard and the API:

: We now support WebRTC, allowing users to connect their audio sources directly to Millis agents via WebRTC. This integration is perfect for a range of applications, including:

Learn more here: WebRTC Integration.

: We've also added SIP Trunking support. With this, you can easily upgrade SIP-based phone systems or call center platforms to connect with advanced voice agents. This includes popular systems like , and more. We support both and for dialing and routing calls. Reach out to us if you'd like to integrate!

: We've added the API, allowing you to obtain a that can be used instead of to define how Millis handles calls. With this, you can pass agent_id, override agent_config, apply temporary agent configurations, and attach metadata to each call, enabling per-call customization for both inbound and outbound calls.

: You can now override agent config (I.e. assign different agent voices) for each phone number, even if they link to the same agent, providing greater flexibility for personalized experiences.

: Enable the agent to decide when to terminate the call itself without waiting for the user. This feature is currently experimental and recommended for use with larger language models like GPT-4o.

: You can now tag phone numbers to better organize and manage your phone list.

: You can now include metadata when using the API.

: Metadata is already forwarded to both the Prefetch Data Webhook and End of Call Webhook. With the new option, agents can now use metadata directly during calls. Additionally, you can pass metadata parameters directly into function calls by using the same parameter names.

Learn more here: Metadata Documentation.