Configure Druid SIP Connectivity

To establish the connection between your AI Agent and your telephony system:

Step 1. Set up Druid SIP general settings

  1. In the Druid Portal, navigate to your AI Agent and select the Channels tab.
  2. Search for 'sip' and click on the Druid SIP card.
  3. In the configuration modal, General tab, configure the following parameters:
  4. Setting Description Mandatory Default value
    SIP FQDN

    The SIP FQDN of the voice AI Agent. Currently supported protocols:TLS, TCP and UDP, on port 5060.

    Info: Copy the SIP FQDN as you will need it to connect the telephony system to Druid.
       
    Enable mTLS

    Turn this toggle on to enforce Mutual Transport Layer Security (mTLS) for SIP connections, which requires a valid client certificate for authentication. When enabled, connecting clients must present a valid client certificate during the TLS handshake.

    IMPORTANT! Only certificates issued by internationally trusted Certificate Authorities (CAs) are supported. Self-signed certificates and certificates issued by private or internal CAs are not supported.
       
    Connection Types

    Select the transport protocol(s) used for SIP signaling. At least one connection type must be enabled; you cannot disable all of them.

    IMPORTANT! For TLS connections, server certificates must be issued by an internationally trusted CA; self-signed certificates and private CA certificates are not supported.
       
    Allowed IPs

    Specify the authorized IP addresses from your telephony/SIP provider allowed to send signaling traffic to Druid SIP.

    Info: You may define up to 10 addresses.

    To add an address entry:

    1. Click the Add button to add a new row.
    2. The Type is set to Simple by default. To enforce a zero-trust security model and prevent unauthorized access, this field requires explicit, individual IP addresses.

      Info: If your telephony provider requires whitelisting IP subnets (such as CIDR blocks or specific IP ranges), please contact Druid Support for advanced security provisioning.
    3. Enter the specific IP address in the IP address field.
    4. Select the transport Protocol and specify the Port if your setup requires fixed routing parameters.
    5. Save the record.

    Use the Edit or Delete icons in the Actions column to manage existing configuration entries.

       

    Phone numbers

    The DID phone numbers assigned to the AI Agent. Enter each number on a new line.

    IMPORTANT! This is the identifier of the voice AI Agent and must be written in the exact same format as it's being sent through the SIP Invite event, by the contact center solution (for example, any E.164 format: +1 321 111 222 3333).

    Yes

     

Now configure the call settings.

Step 2. Configure the call settings

Click the Call Settings tab and configure the following parameters:

Setting Description Mandatory Default value
Enable Audio Recordings Captures and stores the audio recordings of the voice interactions handled by the SIP trunk. No true

DTMF buffer timeout (ms)

The time to wait for the next touch-tone digit before processing the input.

Yes

3000ms

DTMF buffer terminator

The DTMF character used to indicate the end of user input. Leave the field empty to use only the DTMF timeout or the buffer length.

No

#

DTMF max buffer length

The maximum number of digits allowed before the input is automatically sent.

Yes

1

DTMF duplicate filter (ms)

The duration in milliseconds used to ignore accidental duplicate touch-tone inputs.

Yes

20s

Map incoming SIP headers

You can map custom or standard incoming SIP headers sent by your contact center or Session Border Controller (SBC) directly to fields within the Druid [[QueryParams]] entity. This allows you to extract caller contextual data (such as account IDs, priority flags, or custom session tokens) and pass it into flow logic during call setup.

IMPORTANT! Before mapping a SIP header, ensure that the corresponding target field is already created and defined inside the [[QueryParams]] entity structure.

To map incoming SIP headers:

  1. Scroll down to the SIP Headers section and click + Add Header.
  2. In the SIP Headers column, enter the exact name of the incoming header from the telephony provider or contact center. (e.g., x-CustomerId).
  3. In the [[QueryParams]]. column, enter the target field in the [[QueryParams]] entity where the incoming SIP header value will be mapped and stored for use in flow logic (e.g., CustomerId).
  4. Save the mapping.

SIP Codec Negotiation & Priority Order

Info: This feature is available starting with Druid 10.3. In previous releases, the Druid SIP media server used the codec specified in the SDP media offer of the incoming SIP INVITE request.

You can control the order in which supported codecs are advertised during SIP SDP negotiation by enabling Apply Codec Order. By default, Druid uses the recommended codec priority order, but you can customize it based on your audio quality, bandwidth, and compatibility requirements.

Druid supports the following codecs, listed in the recommended default priority order:

Order Codec (PT) Bitrate Description & Characteristics
1 Opus Opus 6–510 kbps (variable) Adaptive audio codec supporting narrowband to fullband audio (8–48 kHz). Provides excellent voice quality, variable bitrate, and resilience to packet loss.
2 G.722 64 kbps Wideband audio (16 kHz) providing clearer speech than G.711 at the same bitrate.
3 PCMU (G.711 μ-law) 64 kbps Narrowband audio (8 kHz) commonly used in North American and Japanese telephony systems.
4 PCMA (G.711 A-law) 64 kbps Narrowband audio (8 kHz) commonly used in European telephony systems.

You can now configure the order in which supported codecs are advertised during SIP SDP negotiation by enabling Apply Codec Order. By default, DRUID uses a recommended codec priority order, which you can customize based on your audio quality, bandwidth, and compatibility requirements.

  1. In the SIP Codec Negotiation & Priority Order section, turn on the Apply Codec Order toggle.
  2. Review the default codec priority order recommended by Druid.
  3. Change the priority order, using either of the following methods:
    • Drag and drop codec rows into the desired order.
    • Use the up and down arrows in the Priority column to move codecs higher or lower in the list.
  4. Save your configuration.
NOTE: The configured priority order determines the order in which supported codecs are advertised during SIP SDP negotiation. It does not guarantee which codec is ultimately selected, as the final codec selection depends on the negotiation between the communicating endpoints.

To restore the recommended priority order at any time, click Reset to Default Order.

Configure the desired speech services following the instructions in the subsequent section.

Step 3. Configure the speech services

Click the Speech tab and define the speech services that Druid SIP will use to process and synthesize voice interactions.

Configure the voice recognition (STT) settings

In the Speech-to-Text (STT) section, configure the following settings:

  1. From the Speech-to-Text Resource dropdown, select a speech resource you already created on the tenant. For more information, see Speech Resource Management and Governance.
  2. Configure how the system detects speech, manages background noise, and allows the user to speak over the AI Agent:
  3. Setting Description Mandatory Default value
    Enable VAD Enables Voice Activity Detection to identify when a user starts or stops speaking. Yes true
    Speech threshold The sensitivity level (0 to 1.0) for detecting speech. Higher values require louder input. Yes 0.5s
    Enable barge-in Allows the user to interrupt the AI Agent while it is speaking. No true

    Barge-in consecutive frames

    The number of consecutive audio frames required to trigger a barge-in interruption. Adjusting this value allows you to balance the AI Agent responsiveness against the risk of false triggers from background noise.

    Default Value: 3 frames (during tech preview).

    A lower frame count makes the AI Agent more sensitive to interruptions, while a higher frame count requires a longer, sustained sound to trigger a response.

    Use the table below to estimate the impact of your frame count on the user experience:

    Audio Unit Definition Approximate Time Frame Equivalent
    Frame Smallest packet of processed audio 20ms 1 frame
    Syllable Linguistic unit of speech 200ms ~10 frames
    Word Complete semantic unit 500ms ~25 frames

    No

    3

  4. If using Druid or ElevenLabs, turn on the Use External VAD toggle to use the STT provider's Voice Activity Detection (VAD) to identify when speech begins and ends.
  5. NOTE: Keep Use External VAD disabled for Azure Speech Services as VAD is managed server-side.
  6. The Language detection mode controls when and how often the system analyzes the incoming audio to identify the spoken language. Select the desired option:
    • None: No automatic language detection is performed.
    • At Start: The language is identified only at the very beginning of the interaction, then the language returned by the AI Agent is used.
    • Continuous: Language detection is performed continuously throughout the conversation.
  7. Configure the detection timeouts:
  8. Timeout Description
    Silence duration (ms) The amount of silence required after a user stops speaking before the system considers the utterance finished and begins processing. Increase this value if users are frequently cut off mid-sentence; decrease it to make the AI Agent more responsive.
    Conversation Idle Timeout Seconds The duration of total inactivity allowed before the call is automatically disconnected. Default value: 120s.

Now configure STT.

Configure the voice synthesis (TTS) settings

In the Text-to-Speech (TTS) section, configure the voice synthesis settings. You can use different TTS service providers for different AI Agent languages.

To add a TTS provider for a specific language:

  1. Click the Add language button.
  2. In the Language field, enter the standard Druid language code (for example, ro for Romanian) that matches either the default or an additional language configured for your AI Agent. For more information, see Druid Supported Languages.
  3. From the Text-to-Speech Resource dropdown, select a speech resource you already created on the tenant. For more information, see Speech Resource Management and Governance.
  4. Save the configuration.

Context Parameters

After the Druid SIP configuration activates, the system automatically provisions the following specific [[ChatUser]] parameters within the conversation context:

  • [[ChatUser]].ChannelId = “druid-sip”. It identifies the channel.

  • [[ChatUser]].Phone – Stores the Calling Party phone number. (The initiator of the call).

  • [[ChatUser]].CalleePhoneNumber – Stores the Called Party phone number. (The destination of the call).

Test speech services and set the output volume

After you configure the speech services, check the result and adjust the volume. You’ll find Test Call and Master Volume at the top of the Speech tab. Use Test Call to talk to the AI Agent before you connect your telephony system. Use Master Volume if the AI Agent’s voice is too loud for your contact center.

Setting Description Mandatory Default value
Test Call

Opens a modal where you can speak directly with your AI Agent to verify the configured speech services in real time. This test bypasses Sip FQDN, IP whitelisting, and connection type rules. For more information, see Test Druid SIP Calls.

   
Master Volume

Sets the volume of the AI Agent’s voice in SIP calls. Master Volume only changes outgoing audio (what the caller hears). It doesn’t change the caller’s audio that the AI Agent receives. Lower the value if the AI Agent’s voice is too loud for your contact center, for example when loud audio causes noise suppression in the contact center codec to fail.

Drag the slider or enter a value from 0 to 100.

No 100

Step 4. Connect your telephony system to Druid

Configure your telephony provider to use the SIP FQDN as the primary routing domain. You can find this value in the Druid SIP Configuration modal.

NOTE: Druid supports SRTP media encryption automatically. If your contact center requires SRTP, Druid automatically negotiates it during the initial SIP handshake with your telephony system—no extra Druid channel configuration needed.

Testing with MicroSIP

For testing purposes, follow these steps to configure MicroSIP:

  1. Download and install MicroSIP from the official website.
  2. Run the application as Administrator.
  3. Set up an account:
    1. Click the Actions icon (the downward arrow) and select Add Account.
    2. Complete the following fields in the Account modal:
    3. Field Description
      Account Name Enter a name for your reference.
      SIP Server Enter the SIP FQDN copied from the Druid Portal.
      SIP Proxy
      Username Enter your designated SIP username.
      Domain

      Enter the details you received from Druid.

      Login
      Password
      Media Encryption

      Select Disabled for standard unencrypted RTP, or choose Optional / Mandatory SRTP. Druid automatically adapts and negotiates SRTP during the SIP handshake whenever requested by MicroSIP.

      Transport

      Select TLS, TCP or UDP. Druid communicates with telephony systems on port 5060.

  4. Click Save to activate the account.