Changelog

Follow up on the latest improvements and updates.

RSS

millis-webrtc-sip
WebRTC Support
: 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:
  • Phone systems with WebRTC capabilities
  • Voice agents in video conferencing platforms like Zoom and Google Meet to interact with participants via voice
  • VoIP systems using WebRTC for real-time communication
Learn more here: WebRTC Integration.
SIP Trunking Support
: 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
Asterisk based, Vicidial
, and more. We support both
Elastic SIP Trunking
and
SIP Endpoint
for dialing and routing calls. Reach out to us if you'd like to integrate!
Register Call API
: We've added the
register_call
API, allowing you to obtain a
call_id
that can be used instead of
agent_id
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.
Override Agent Config per Phone Number
: 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.
Agent Terminate Call Config (Experimental)
: 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.
Tag Phone Numbers
: You can now tag phone numbers to better organize and manage your phone list.
Add Metadata for Outbound Calls
: You can now include metadata when using the
start_outbound_call
API.
Use Metadata in Call
: Metadata is already forwarded to both the Prefetch Data Webhook and End of Call Webhook. With the new
include_metadata_in_prompt
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.
Bring Your Own ElevenLabs Key
: You can now bring your own ElevenLabs API key, and we won’t charge you when using ElevenLabs as the voice provider. Plus, you can easily import all custom voices from your ElevenLabs account to use with your Millis agents.
ElevenLabs Trending Voices
: The trending voice list from ElevenLabs is now available in popular languages like English, French, German, Dutch, and more.
SDK Updates
:
  • Mute/Unmute Functions: New SDK updates include mute/unmute capabilities for agents.
  • onfunction
    Event: We've added an
    onfunction
    event, so the web SDK knows when a function is triggered by the agent.
millis-neets
We’ve added Neets TTS, the
cheapest TTS provider
on the market at just
$1 per million characters
! Neets.ai offers the most
competitive pricing
in the industry with decent quality and latency. Supporting over 80+ languages, we're excited to include Neets in our growing list of TTS voice providers. This addition unlocks even more use cases for conversational voice AI across diverse languages and markets.
millis-deepgram
We've integrated Deepgram TTS into Millis! From our testing, it offers decent quality with good latency and is a very affordable option for voice synthesis. Currently, it supports English only, but we're hopeful for more language options in the future.
millis-languages
More Language Support (Beta)
: We're excited to expand language support with
Whisper Large v3
, the latest state-of-the-art STT model. We've added support for 40 more languages, including
Hebrew, Arabic, Tamil, Bengali, Gujarati, and Marathi
. In total, Millis voice agents now support
85 languages
!
Multilingual Support (Experimental)
: Also based on Whisper Large v3, this new experimental feature allows agents to auto-detect the language the user is speaking and respond accordingly. No more fixed language settings—agents can seamlessly switch between languages during a conversation.
Auto-Fill Responses Config
: We've added a new option to handle delayed responses from custom LLMs. Agents can now automatically say predefined phrases if a response takes longer than expected. Configure it like this:
{flow: {auto_fill_responses: {messages: ["Let me check", "Hold on"], response_gap_threshold: 1000}}}
Knowledge Base API
: You can now manage your agent's knowledge base via API! This includes the ability to upload files, add them to the agent, delete files, and more—giving you greater control and flexibility in managing your knowledge assets.
millis-exotel
We’re excited to announce the addition of
Exotel
as a supported telephony provider on Millis! With this update, we now support a total of
four providers
, further expanding our global coverage. Exotel is available in
60+ countries
and is a popular option in
India
, offering even more flexibility for your telephony needs.
Trigger Outbound Calls from Dashboard
: You can now initiate outbound calls directly from the dashboard, no API required! Plus, an outbound campaign system for mass users is coming soon.
Language Switching Config
: Agents can now switch languages mid-call if the user requests it (e.g., "Can you speak Spanish?"). Set this option in the agent config with:
{switch_language: {languages: ['en', 'es', ...]}}
.
Custom LLM Streaming Phrase
: If you know a custom LLM response will take time, you can stream an initial phrase for the agent to say first with the option
flush = true
, then process and stream the rest later. With
flush = true
agent will generate phrase audio right away to keep the conversation smooth and responsive.
ElevenLabs Improvements
: We've made further optimizations to ElevenLabs, ensuring even faster streaming for a better real-time experience.
Load More