> For the complete documentation index, see [llms.txt](https://docs.aisera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisera.com/aisera-platform/product-channels/interactive-voice-response-ivr/channel-settings-for-ivr.md).

# Channel Settings for IVR

Use IVR settings when you want to add a voice channel to Aisera assistant. Before adding IVR channel, you have to make sure to add integrations for STT (Speech to Text) and TTS (Text to Speech)

### Step 1 - IVR channel - Basic settings

It shows the name of the channel. The secondary channel lists the alternate response method for certain answer types. For example - serve KB articles via email.

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2FtSwDSTj2Yg9Uz5VN5GvT%2Fedit_channel_step1.gif?alt=media&amp;token=ece115e1-f157-464e-8118-1ab2a6ef5221" alt=""><figcaption></figcaption></figure></div>

| Parameter    | Description                        |
| ------------ | ---------------------------------- |
| Channel Name | Create a name for your IVR channel |

### Step 2 - IVR channel - General settings

The second step of the IVR Channel settings allows you to include content that you want the application/bot to play in specific scenarios.

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2F3S4FDBE1r4KL3RwKqcUg%2Fchannel_step2.gif?alt=media&amp;token=4360aae3-9e4b-45f8-b7aa-ac858c4cecfb" alt=""><figcaption></figcaption></figure></div>

The follow table describes the parameters on the Step 2 window.

<table><thead><tr><th width="323.5760498046875">Parameter</th><th>Description</th></tr></thead><tbody><tr><td>Language</td><td>Language code of the Aisera assistant</td></tr><tr><td>Intro Flow Trigger Phrase</td><td>Trigger a flow with this phrase. Used for initializing and dynamically welcoming the user</td></tr><tr><td>Post Welcome Message Flow</td><td>Specify a custom workflow that triggers after the IVR Channel plays the init/welcome message, such as when you want to authenticate the user before they proceed with the assistant.<br>Make sure the end of the workflow asks the user - "How can I help you?". That will make sure the user response is treated as a new request after the post welcome message flow.</td></tr><tr><td><p></p><p>No User Input Timeout</p></td><td>No user input timeout in milliseconds. Bot will react with message or hangup based on other setting below after this timeout </td></tr><tr><td>No User Input Giveup Retries</td><td>Number of times the no user input will be triggered before hangup</td></tr><tr><td>No User Input Bot Prompts</td><td>Voice prompts to be played on no user input event. You can specify multiple inputs separated by a new line. The bot will select one of the prompts randomly.</td></tr><tr><td>No User Input Bot Disconnect Prompts</td><td>Voice prompts to be played on no user input event. You can specify multiple inputs separated by a new line. The bot will select one of the prompts randomly.</td></tr><tr><td>User Input Not Understood Prompts</td><td>Prompt to be played when STT model was not able to confidently transcribe ( understand) the user’s input.</td></tr><tr><td>Bot Error Prompt</td><td>The prompt played when a system error occurred. </td></tr><tr><td>Bot Transfer Error Prompt</td><td>The prompt to be played when error happens during transfer of call. </td></tr><tr><td>Hangup On Transfer Failure</td><td>Check this box, if you want to hangup after a failed transfer after playing a message.</td></tr><tr><td>Call Recording</td><td>Check this box if you would like to record the caller audio voice on the request details page.</td></tr></tbody></table>

### Step 3 - IVR channel - Speech to text settings

The third step allows you to specify speech-to-text settings, as shown below.

<div align="left"><figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdcL1l1-sTTDyqkf79VL0L8veNV5cm5U0c3o2L6aMraIwbDzbwhpdtNlyrrLjjK_1JQxn-e1GdlbfqqKzEk6aLSHCs8kLcw1RJ23UcJtlOuB8OshaKh5n4c_csJLbQW_2XbA-Zr?key=14Ul38_lzWo2kTaBvYKeBQ" alt="" width="563"><figcaption></figcaption></figure></div>

Select the STT integration that you would like to use with this channel

### Step 4 - IVR channel - Text to Speech settings

The fourth step allows you to specify text-to-speech settings, as shown below.

<div align="left"><figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXcBnLn4dmk0JfzSVdl3C1uK4m1oj84tlxHqJyMi1c1-10nHhBNef1B0jZETTY_kyqInpSvwtpfy7MqkavMpp8XMIGglfYqXWrSkhvmrcGF0aZcrg1zfsPnRejgYyeWMSoBLRnkA?key=14Ul38_lzWo2kTaBvYKeBQ" alt="" width="563"><figcaption></figcaption></figure></div>

| Parameter                 | Description                                                                                                       |
| ------------------------- | ----------------------------------------------------------------------------------------------------------------- |
| Primary TTS integration   | Select the primary TTS integration that you would like to use with this channel                                   |
| Voice Name                | This is the ID of the voice talent (speaker) to be used to respond to caller                                      |
| Secondary TTS integration | Select the secondary TTS integration that you would like to use with this channel                                 |
| Voice Name                | This is the ID of the secondary voice talent (speaker) to be used to respond to caller when primary does not work |

### Using a Secondary Channel with IVR

When you are using a voice channel with your application/bot, you can add a secondary channel, such as email, or messaging to deliver a long or detailed version of the response while your voice channel provides a summary of the fulfillment. This secondary channel serves as a backup or specialized routing path.&#x20;

The secondary channel feature is an asynchronous delivery experience for **Voice** channels when a query produces a **RAG-generated response**. The caller immediately hears a brief, high-level summary over the phone. The complete grounded answer, including detailed instructions and citations, is generated in the background and delivered to a configured secondary channel, such as email or messaging, through a Customization Flow.

**Scope and applicability:** This feature applies only to **IVR channels** and to v2 (and later) applications/bots.. It does not trigger for other channels, casual conversations, CDS clarifications, or fallback dialogs.

#### Voice playback and delivery behavior <a href="#voice-playback-and-delivery-behavior" id="voice-playback-and-delivery-behavior"></a>

| Configuration                                      | Caller hears                                                                  | Secondary channel                                                                    |
| -------------------------------------------------- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| Secondary channel disabled                         | Summary response                                                              | No delivery                                                                          |
| Secondary channel enabled; Summary Enabled = True  | Summary response plus custom suffix                                           | \[**Selected** **Conversational AI Policy**] RAG response delivered through the Flow |
| Secondary channel enabled; Summary Enabled = False | Custom suffix only; falls back to the Summary response if the suffix is empty | \[**Selected** **Conversational AI Policy**] RAG response delivered through the Flow |

### Secondary Channel Setup <a href="#administration-and-setup" id="administration-and-setup"></a>

#### Prerequisites <a href="#prerequisites" id="prerequisites"></a>

* The interaction must use a **Voice** channel.
* The turn must produce a **RAG response** through knowledge retrieval.
* A secondary-channel Customization Flow must be configured for dispatch.

#### Voice channel configuration <a href="#voice-channel-configuration" id="voice-channel-configuration"></a>

1. Open **Admin UI** → **Voice Channel Settings**.
2. Turn on `useSecondaryChannel`.
3. Select or specify the Customization Flow ID in `secondaryChannelCustomizationFlowId`.
4. Configure `secondaryChannelSummaryEnabled`:
   * **ON:** Play the Summary response followed by the suffix.
   * **OFF:** Play only the custom suffix.
5. Configure `secondaryChannelSummarySuffix` with a custom text-to-speech notice, such as *“I am sending detailed answer over secondary channel…….”*

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2FxEJaLxeKe2qg9qVOAy02%2Fsecondary_one.png?alt=media&amp;token=9696ef75-30b3-4e77-b113-f603da3c3979" alt="" width="563"><figcaption></figcaption></figure></div>

### **Secondary Channel Workflow Requirements** <a href="#customization-flow-requirements" id="customization-flow-requirements"></a>

For administrators and flow designers building the secondary channel Flow:

* **Input Variables Received:**
  * `ragResponse` *(String)* — Full grounded answer generated per bot policy.
  * `userQuery` *(String)* — Original user question.
  * `citations` *(String)* — Formatted citation links.
* **Flow Design & Context Handling:**
  * The Flow should use the **Message Node** to record the delivered answer into the conversation context and transcript upon successful delivery.
* **Output Variable Returned:**
  * `success` *(Boolean)* — Return `true` on successful dispatch to ensure metrics and audit logs accurately record the delivery event.

<div align="left"><figure><img src="https://3281977978-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvBFXjH9S1CAy9f5hzg5Q%2Fuploads%2FHWOLR2Ym8lKoPZXYON7n%2Fsecondary_two.png?alt=media&amp;token=66479f1b-07b1-4daa-a494-a12920487ac3" alt="" width="563"><figcaption></figcaption></figure></div>

**Expected outcome:** Voice callers receive fast, summary answers without waiting for lengthy playback, while the complete, policy-controlled RAG response remains available through their designated secondary channel.