> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice channels

[Back to voice channels](https://koreai.mintlify.site/agent-platform/channels.md#voice-channels)

## Set up Realtime LLM Voice channel

Realtime LLM Voice is a voice channel that handles live voice conversations through a single provider-native speech session. It supports Realtime LLM models (such as OpenAI Realtime and Gemini Live) through the Kore.ai Voice Gateway (KoreVG) or a Bring Your Own SIP connection.

Unlike the STT → LLM → TTS pipeline that Pipeline Voice uses, a provider-native realtime model owns the live audio conversation. KoreVG handles telephony, connection routing, bounded session state, traces, and the call lifecycle.

> [!TIP]
>
> Studio also provides in-product guidance. On the **Realtime LLM Voice** channel page, click **Setup instructions** to open a step-by-step panel that covers connection creation, provider and phone routing, call quality validation, and security, latency, and reliability boundaries.

### Create a Realtime LLM Voice channel

To create a Realtime LLM Voice channel, go to **Deployments** > **Channels** > **Voice** > **Realtime LLM Voice** > **New connection** and complete the following steps in order.

**1. Set up the connection**

On the **New Realtime LLM Voice Connection** page, provide the following fields.

| Field | Description |
| - | - |
| **Display Name** | A label for the connection. |
| **Connection Name** | A stable system name for the connection, up to 255 characters. Use an environment-specific identifier such as `realtime-voice-production`. It's an external identifier, not a phone number or a shared gateway account. |
| **Environment** | The deployment the connection binds to. Select an environment whose active deployment contains the realtime-compatible agent, tools, model policy, and welcome behavior. Select an environment to follow its active deployment automatically, or leave the default to use the working copy. When no environment has an active deployment yet, create a deployment first to bind the connection to a published environment. |
| **Provider Verification Strength** | Controls how strictly the platform trusts the provider's identity assertions for session continuity and linking. **Weak** is the default. Choose **Strong** only for channels or providers whose identity assertions you trust. |
| **Initial Status** | **Active** connections are usable immediately. **Inactive** connections stay saved but disabled until you activate them. Use **Inactive** while the provider and phone routing are incomplete. An **Active** phone-routed connection without a provisioned number can't receive production PSTN calls. |

**2. Create the connection**

Click **Create**.
\[!NOTE] Create the connection before you configure voice details. The connection record must exist before Studio can provision a phone number and save provider-specific realtime settings.

### Configure the Realtime LLM Voice channel

Once the channel is created, open it from the **Realtime LLM Voice** connections list. The connection has three tabs: **Settings**, **Speech**, and **Testing**. The **Settings** tab holds the voice provider and call routing. The **Speech** tab holds realtime orchestration, the S2S provider, and advanced voice behavior. The **Testing** tab holds the shareable softphone link.

**1. Choose a call routing option (Kore.ai Voice Gateway)**

On the **Settings** tab, under **Realtime LLM Voice Settings**, set **Voice Provider** to **Kore.ai Voice Gateway** or **Bring Your Own SIP**. If you choose **Kore.ai Voice Gateway**, set the following under **Call routing**. Choose how calls reach this agent. Enable **Soft Phone** for browser testing, and add a phone number (DID) when the channel needs a real phone number.

| Route | Description |
| - | - |
| **Soft Phone** (FREE) | Dial the agent from your browser with no DID purchase or telephony charges. Use it for evals, QA, and demos. **Launch dialer** opens the browser dialer. |
| **Phone Number (DID)** | Purchase a real phone number through Twilio. Disable this route to stop DID listing and call routing while keeping the number saved. The DID and IP address combination must be unique across Bots, Projects, and Workspaces. |

Keep KoreVG as the managed telephony gateway unless your platform owner has approved another provider. Confirm that the realtime provider you plan to use is available for your tenant and environment.

> [!NOTE]
>
> If you select **Phone Number (DID)**, complete the next step. If you selected **Voice Provider: Bring Your Own SIP** instead, skip to step 3.

**2. Configure the phone number (DID only)**

* Set **Provider** to **Twilio**.
* Toggle **Inbound calls** (routes calls from this number into the voice agent).
* Toggle **Outbound calls** (allows this number for campaign dial‑out).
* Select a **Country**, **Number Type**, and optional **Area Code**.
* Choose **Search Available Numbers** to list matching numbers.

Buy or assign a Twilio‑backed number from the saved connection’s settings.

* Confirm the number is bound to this connection before activation.
* After assignment, the number appears in the **Phone Number** field.
* Select **Remove** to unbind the number from the connection.

**3. Configure SIP settings (Bring Your Own SIP only)**

If you chose **Bring Your Own SIP**, the **Call routing** options are replaced by a **SIP Configuration** section on the **Settings** tab. Set the following fields.

| Field | Description |
| - | - |
| Our SIP Server Address | Read-only address of the Kore.ai SIP server. Select **Copy** to copy it. Configure your SIP provider to send INVITE to this address. |
| SIP Gateway IPs / CIDRs | Your provider's SIP source addresses. Enter IPv4 addresses (optionally with a port) or CIDR ranges, separated by commas. For example, `203.0.113.50:5080, 3.80.16.0/23`. |
| SIP Termination URI | The IP address or domain name the platform sends outbound SIP traffic to. For **IP Address**, enter up to 10 distinct IPv4 addresses separated by commas, for example `198.51.100.10, 198.51.100.11`. **Domain Name** accepts one domain name. Multiple IP addresses configure multiple destinations; they don't guarantee failover, which depends on your carrier or gateway. |
| Port | The SIP port of the termination URI. Defaults to 5060. Change it if the carrier uses a different SIP port. |
| Transport | The transport protocol used for SIP signaling, for example UDP. |
| Send OPTIONS ping | Probes the endpoint and stops routing to it while it does't answer. |
| Outbound calls | Allows campaigns and dial-out to call through the SIP termination URI. A SIP termination URI is required when this option is selected; otherwise Save is rejected. |
| DID / Phone Number | The phone number (DID) your SIP provider routes to this SIP gateway. |
| Enable E.164 (leading +) | Prepends a leading + to outbound numbers sent to the carrier. By default, this is on, because international (full E.164) numbers require it. Turn it off only for local or national-format numbers; otherwise the leading + misroutes them. |

**4. Configure the voicemail message**

Use the **Voicemail message** card on the **Settings** tab to set the message the agent plays when an outbound call reaches an answering machine. When an outbound call asks to leave a voicemail and an answering machine picks up, this message plays after the beep and the call hangs up. Turn on the **Voicemail message** toggle to show the message settings.

> [!NOTE]
>
> Campaign calls aren't affected. Only outbound calls that ask to leave a voicemail use this message.

Under **Default message**, set the following fields.

| Field | Description |
| - | - |
| **Message type** | How the message is delivered. Select **Text spoken by a voice** to have a voice read the text you enter. |
| **Message** | The text the agent speaks, up to 500 characters. For example, `Hi {{_metadata.firstName}}, this is Acme Health calling about your appointment. Please call us back at 555-0100.` Placeholders such as `{{_metadata.firstName}}` are filled in when the call is made, so the spoken message can be longer than the character count. A message that ends up over the limit isn't played. |
| **Voice provider** | The text-to-speech credential set that speaks the message, for example **Microsoft Speech Credentials**, **Emotech (TTS) Credentials**, **ElevenLabs (TTS) Credentials**, or **Deepgram Speech Credentials**. The default is **No voice chosen**. |

To add a message for another language, under **Messages for other languages**, do the following. A language message is used when the call's language matches. Every other call gets the default message.

1. Select **Add a language**.
2. In **Language**, choose a language.
3. Set **Message type**, **Message**, and **Voice provider**, as described in the previous table.
4. To remove a language message, select the delete icon next to **Language**.

**5. Set SIP header trust and save the connection settings**

At the bottom of the **Settings** tab, for either voice provider, set the following.

| Field | Description |
| - | - |
| **Trust inbound SIP headers** | Off by default. Turn it on only if your SBC sets or overwrites these headers. If the headers can arrive from the caller, the value isn't trustworthy. When on, transfer headers configured to pass through from the inbound call (for example, `User-to-User`) are sent on the transfer. When off, they're dropped. |
| **Connection Name** | The system name of the connection. Select the copy icon to copy it. |

Click **Save Changes** to apply the settings.

**6. Configure Realtime LLM Voice settings**

On the **Speech** tab, set the following fields.

* **Realtime orchestration**: Select how runtime coordinates the conversation flow and business tool execution for realtime voice interactions. Realtime orchestration determines whether the realtime model or runtime controls conversation progression and business actions, such as bookings, orders, and payments.

  | Mode | Description | Recommended for |
  | - | - | - |
  | **Legacy - model-selected tools** | Preserves the existing behavior where the realtime model manages both the conversation and business tool selection. | Existing agents and backward compatibility. |
  | **Runtime Guarded - hybrid freeform (recommended)** | Allows the realtime model to conduct the conversation naturally while runtime validates tool execution and context updates against the current FLOW step. Business tools execute only when they belong to the active FLOW step, preventing out-of-order actions while maintaining the authored FLOW. | New realtime voice agents that require natural conversations while maintaining FLOW integrity. |
  | **Runtime Owned - canonical turn** | Runtime controls every conversation turn and executes the FLOW exactly as authored. The realtime model handles conversational responses but cannot invoke business tools directly. | Workflows involving payments, bookings, orders, or other irreversible business actions and highly deterministic flows. |

  > [!NOTE]
  >
  > * Changes to the orchestration mode apply only to new realtime sessions. Calls already in progress continue using the mode that was active when the session started.
  > * Existing channel configurations without a configured orchestration mode continue to use Legacy behavior. Don't leave a line on Legacy.
  > * The mode applies to every agent a call can reach. **Runtime Owned** runs each caller turn through the runtime, so FLOW steps, tool contracts, and confirmations work as in chat. **Runtime Guarded** protects FLOW steps only. A reasoning agent's tools run whenever the model calls them, within their contracts.

* **Response wording owner**: Select who generates the wording of responses for realtime voice conversations. This setting is available only when the Realtime orchestration mode is set to **Runtime Owned - canonical turn**.
  * **Runtime text (recommended)**: Runtime generates the response text. This option provides consistent response generation.
  * **Provider-grounded voice**: Uses the realtime voice provider to generate spoken responses while runtime continues to control conversation flow and business actions. This option is available only for Gemini Live. For unsupported or unsafe conversation turns, it automatically falls back to runtime-generated text responses.

* **Semantic convergence**: Semantic Convergence determines how the platform coordinates with the realtime voice provider during a voice interaction. Controls whether realtime voice turns use the coordinated utterance runtime. This setting is available only when the realtime orchestration config is set to **Legacy mode**. The **Effective at runtime** line below the setting shows the mode currently in effect.

  | Mode | Description | Recommended use |
  | - | - | - |
  | **Off** | Uses the legacy realtime voice execution model. The realtime provider executes tool calls directly without semantic coordination. | Use for backward compatibility with existing voice applications. |
  | **Shadow** | Uses the legacy execution model while collecting diagnostics to compare legacy behavior with semantic convergence. Doesn't affect customer interactions. | Use for validation, testing, and migration before enabling **Enforce**. |
  | **Enforce** | Uses semantic convergence to route voice turns through the platform's coordinator, ensuring tool execution and business logic are processed consistently with the agent runtime. | Recommended for new realtime voice deployments and production environments requiring consistent behavior across voice and text. |

* **S2S Provider**: The realtime speech-to-speech model the channel uses. Select an approved realtime provider and model, and match its audio format, locale, voice, and tool-calling capabilities to the agent. Select one of the following: **Amazon Nova Sonic (S2S)**, **Azure OpenAI Realtime**, **Grok Realtime (S2S)**, **Google Gemini Live**, or **OpenAI Realtime**. Each option shows which credentials it uses:

  | Provider | Credentials used |
  | - | - |
  | **Amazon Nova Sonic (S2S)** | Voice Service credentials (Amazon Nova Sonic (S2S) Credentials). |
  | **Azure OpenAI Realtime**, **Grok Realtime (S2S)**, **Google Gemini Live**, **OpenAI Realtime** | The project-selected model connection. See **Realtime model connection** below. |

* **Realtime model connection**: Shown for every S2S provider except Amazon Nova Sonic, which authenticates via Voice Service credentials instead. Selects the project-pinned realtime model this provider uses. It shows `Use project realtime model` until a workspace admin adds one. The **Source** line below the dropdown shows where the model comes from, and the deployment uses this exact model connection. To add one:

  1. Configure the model under [Voice Services](https://koreai.mintlify.site/agent-platform/administration/ai-configuration.md#voice-services), then add it to the [model catalog](https://koreai.mintlify.site/agent-platform/administration/ai-configuration.md#model-catalog) as an LLM provider.
  2. In the project, go to **Settings** > **Models** and add the model you configured at the workspace level. See [Models](https://koreai.mintlify.site/agent-platform/administration/general-settings.md#models).

* **Provider-specific settings**: After you select an S2S provider, a configuration section for that provider appears. Expand the provider below to see its settings.

  > [accordion] Amazon Nova Sonic
  >
  > Under **Amazon Nova Sonic Configuration**, set the following fields.
  >
  > | Field | Description |
  > | - | - |
  > | **Voice** | The voice Nova Sonic uses to speak to callers. Default: **Tiffany**. |
  > | **Model** | The Amazon Bedrock model ARN, for example `arn:aws:bedrock:us-east-1::foundation-model/amazon.nova-2-sonic-v1:0`. |
  > | **Maximum tokens** | The maximum number of tokens in a model response. Default: `1024`. |
  > | **Temperature** | Controls response randomness. Lower values give more predictable responses; higher values give more varied responses. Default: `0.70`. |
  > | **Top P** | Limits the model to the smallest set of likely tokens whose combined probability reaches this value. Default: `0.90`. |
  > | **Endpointing sensitivity** | How quickly Nova decides the caller has finished speaking. **Medium** (default) suits general conversation. **High** responds sooner but may interrupt callers. **Low** allows more pause before responding. |
  >
  > **Pending tool fillers**
  >
  > Turn on **Pending tool fillers** to let Nova speak a brief hold phrase when a project tool is still running. Fast tools finish without a filler.
  >
  > | Field | Description |
  > | - | - |
  > | **Filler delay (milliseconds)** | Nova speaks only if the tool is still pending after this delay. Leave empty to use the default of `900` ms. |
  > | **Tool filler instruction** | The instruction Nova follows to generate the hold phrase. Use `{{toolName}}` to insert the name of the running tool. Default: `The tool {{toolName}} is still in progress. Briefly tell the caller that you are working on it.` |
  >
  > **Coordinator turn filler**
  >
  > Turn on **Coordinator turn filler** to let Nova speak a short hold phrase during convergence-enabled coordinator turns while Runtime decides and executes the turn.
  >
  > | Field | Description |
  > | - | - |
  > | **Coordinator filler instruction** | The instruction Nova follows to generate the hold phrase. Default: `Briefly tell the caller that you are still working on their request.` Runtime sends this as native cross-modal input and keeps its transcript out of the canonical conversation history. |
  >
  > **Advanced voice behaviour**
  >
  > | Field | Description |
  > | - | - |
  > | **Failed tool call fallback** > **Tell the caller and end the call** | When a Nova tool call fails, Nova says a short apology and ends the call. Off by default. |
  > | **Guarded flow delivery** > **Answer wording** | Controls who owns the wording of a Runtime answer in a guarded flow. - **Today's behavior** (default): The voice model says the Runtime answer in its own words. - **Exact**: The voice model says the answer word for word. |
  > | **Guarded flow delivery** > **Acknowledgement** | Controls how the agent responds when a step is still running after the silence budget. - **Off** (default): No acknowledgement is spoken. - **Authored phrases**: Speaks one of your phrases, in turn. With no phrase configured, it stays off. - **Model's own lead-in**: The voice model briefly acknowledges, in its own words, what the caller just said, and then gives the flow's answer. The phrases are used only by **Authored phrases**. |
  > | **Guarded flow delivery** > **Acknowledgement phrases** (Optional) | The phrases the agent speaks when **Acknowledgement** is set to **Authored phrases**. Enter one phrase per line, for example, `One moment.` and `Let me check that for you.` You can add up to 12 phrases of 80 characters each. Phrases must be unique and can't contain any of these characters: ``< > { } [ ] ` \``. |
  > | **Guarded flow delivery** > **Silence budget (ms)** (Optional) | How long a step can keep running before the agent acknowledges. Used by **Authored phrases** and **Model's own lead-in**. Enter a value from `100` to `5000` ms. Leave empty to use the default of `500` ms. |
  >
  > The **Guarded flow delivery** settings are channel defaults for guarded realtime flows only. They apply when **Realtime orchestration** is set to **Runtime guarded**, and your values are kept when it's set to another mode. An agent or step can override each value in its ABL. Changes apply from the next call.
  >
  > Also configure the **Advanced voice behaviour** settings that apply to all providers, described after the provider list.

  > [accordion] Azure OpenAI Realtime
  >
  > Under **Azure OpenAI Realtime Configuration**, set the following fields.
  >
  > | Field | Description |
  > | - | - |
  > | **Voice** | The voice used to speak to callers. Default: **Marin (recommended)**. |
  > | **Temperature** | Controls response randomness. Range: **Focused** (`0.6`) to **Creative** (`1.2`). Default: `0.8`. |
  >
  > **Turn detection**
  >
  > | Field | Description |
  > | - | - |
  > | **Speech detection sensitivity** | Adjusts how readily the model detects speech. Default: `0.5`. |
  > | **Silence Duration (ms)** | How long the caller must be silent before the turn is treated as complete. Default: `700`. |
  > | **Prefix Padding (ms)** | Audio kept before detected speech so the start of the caller's utterance is preserved. Default: `300`. |
  >
  > Also configure the **Advanced voice behaviour** settings that apply to all providers, described after the provider list.

  > [accordion] Grok Realtime
  >
  > Under **Grok Realtime Configuration**, set the following fields.
  >
  > | Field | Description |
  > | - | - |
  > | **Voice** | The voice used to speak to callers. Default: **Ara**. |
  > | **Temperature** | Controls response randomness. Range: **Focused** (`0.0`) to **Creative** (`2.0`). Default: `0.8`. |
  > | **Threshold** | Controls speech detection. Range: **Sensitive** (`0.0`) to **Conservative** (`1.0`). Default: `0.5`. |
  > | **Silence Duration (ms)** | How long the caller must be silent before the turn is treated as complete. Default: `500`. |
  > | **Prefix Padding (ms)** | Audio kept before detected speech so the start of the caller's utterance is preserved. Default: `300`. |
  >
  > Also configure the **Advanced voice behaviour** settings that apply to all providers, described after the provider list.

  > [accordion] Google Gemini Live
  >
  > Under **Gemini Live Configuration**, set the following fields.
  >
  > | Field | Description |
  > | - | - |
  > | **Voice** | The voice used to speak to callers, for example **Puck — Upbeat**. |
  > | **Enable context window compression** | Lets Gemini compress older session context so long-running Live conversations can continue beyond the model's context window. Off by default. |
  > | **Temperature** | Controls response randomness. Range: **Deterministic** (`0.0`) to **Creative** (`2.0`). Default: `0.8`. |
  >
  > **Tool response scheduling**
  >
  > | Field | Description |
  > | - | - |
  > | **Tool response scheduling** | Controls how Gemini resumes after a final tool result. **Interrupt** responds immediately to the final result. **When idle — finish the current response first** (default) waits for the current response to finish. **Silent** retains the final result without speaking right away. Progress and filler updates always wait until Gemini is idle. |
  > | **Pending tool fillers** | Lets Gemini Live acknowledge long-running project tools while the original tool call remains pending. Off by default. |
  >
  > **Realtime turn filler**
  >
  > Separate from project Voice Fillers. Applies only to Google or Vertex realtime S2S calls while semantic convergence is set to **Enforce**.
  >
  > | Field | Description |
  > | - | - |
  > | **Native turn filler** | Lets Gemini speak a short hold phrase while Runtime settles an enforced turn. It never applies to transfers, handoffs, or protected playback. |
  > | **Generative native filler** | Lets Gemini choose a short, contextual hold phrase in the current language instead of using the deterministic phrase pool. |
  > | **Generative filler prompt override** | Overrides the prompt Gemini uses to generate the hold phrase. Default: `Reply with a short, natural hold phrase in the current language.` |
  >
  > **Filler delivery safeguards**
  >
  > Shared by pending-tool and realtime turn fillers.
  >
  > | Field | Description |
  > | - | - |
  > | **Settlement watchdog** | Time allowed for filler generation or a held final response to settle before Runtime releases the safe fallback. Accepted range: `1000`–`60000` ms. Leave empty to use the platform default of `10000` ms. |
  >
  > **Voice activity detection**
  >
  > Controls when Gemini starts listening to a caller turn and how long it waits before closing that turn.
  >
  > | Field | Description |
  > | - | - |
  > | **Start Sensitivity** | Higher detects speech sooner but may trigger on noise. Lower waits for a stronger speech signal. Default: **Default**. |
  > | **End Sensitivity** | Higher ends turns sooner for lower latency. Lower allows longer pauses before Gemini responds. Default: **Default**. |
  > | **Silence Duration (ms)** | Milliseconds of non-speech before Gemini closes the caller turn. Increase to allow pauses; decrease for faster responses. Default: `100`. |
  > | **Prefix Padding (ms)** | Milliseconds of detected speech required before Gemini commits a speech start. Lower values catch shorter utterances but can increase false starts. Default: `20`. |
  >
  > **Caller transcription**
  >
  > | Field | Description |
  > | - | - |
  > | **Caller language** (Optional) | The language callers speak, such as `en-US`. If left empty, Gemini guesses the language on every turn, which can turn English into another script. The call's language setting, when there is one, takes precedence. |
  >
  > **Silent-turn recovery**
  >
  > | Field | Description |
  > | - | - |
  > | **Recover silent turns** | Re-prompts, then restarts, a Gemini session that stays silent when it owes the caller an answer. |
  > | **Recover unanswered caller turns only** | Limits recovery to caller turns that received no answer. Included automatically when **Recover silent turns** is on. If Gemini hears the caller but doesn't respond within 8 seconds, the Gemini session restarts with the caller's words, without re-prompting tool results. |
  >
  > **Advanced voice behaviour**
  >
  > | Field | Description |
  > | - | - |
  > | **Silent resume recovery** > **Recover a silent resumed session** | Starts a fresh Gemini session when a resumed one connects but never speaks. Off by default. |
  >
  > Also configure the **Advanced voice behaviour** settings that apply to all providers, described after the provider list.

  > [accordion] OpenAI Realtime
  >
  > Under **OpenAI Realtime Configuration**, set the following fields.
  >
  > | Field | Description |
  > | - | - |
  > | **Voice** | The voice used to speak to callers. Default: **Marin (recommended)**. |
  >
  > **Turn detection**
  >
  > Tune how OpenAI detects when speech starts and when the caller has finished speaking.
  >
  > | Field | Description |
  > | - | - |
  > | **Turn detection mode** | How OpenAI detects turns, for example **Server VAD - audio activity**. |
  > | **Speech detection sensitivity** | Range: **More sensitive** (`0.0`) to **More conservative** (`1.0`). Lower values pick up quieter speech; higher values reduce background-noise triggers. Default: `0.5`. |
  > | **Silence Duration (ms)** | Quiet time before OpenAI treats the caller turn as complete. Default: `700`. |
  > | **Prefix Padding (ms)** | Audio kept before detected speech so the beginning of the caller's utterance is preserved. Default: `300`. |
  >
  > **Noise reduction**
  >
  > The provider filters the caller's audio before it detects speech and before the model hears it, so background sound starts fewer false turns.
  >
  > | Field | Description |
  > | - | - |
  > | **Noise reduction** | Select the type of noise reduction to apply to the caller's audio. - **Off (default)**: No noise reduction is applied. - **Near field - handset or headset**: Use when callers speak close to the microphone, such as on a handset or headset. - **Far field - speakerphone or room microphone**: Use when callers are farther from the microphone, such as on a speakerphone or a room microphone. |
  >
  > > [!NOTE]
  > >
  > > Noise reduction removes noise, not other voices. Background talkers and echo of the agent still reach the model. This setting is separate from the gateway's **Noise isolation** setting under **Advanced voice behaviour**.
  >
  > **Caller transcription**
  >
  > How the caller's speech is written down. This text is stored as the caller's turn and is what the agent checks answers against.
  >
  > | Field | Description |
  > | - | - |
  > | **Caller transcriber** | The transcription model, for example **Whisper (default)**. |
  > | **Caller language** (Optional) | The language callers speak, such as `en-US`. If left empty, the transcriber guesses the language on every turn, which can turn English into another script. |
  > | **Words to expect** | Brand names and terms callers use, for example `Acme, Rewards, email addresses spelled out letter by letter`. Used by Whisper and GPT-4o Transcribe. |
  >
  > > [!NOTE]
  > >
  > > Never put a caller's own details in **Words to expect**. The transcriber would then hear them from anyone.
  >
  > **Realtime turn filler**
  >
  > Applies only to OpenAI Realtime calls while semantic convergence is set to **Enforce**. Off by default.
  >
  > | Field | Description |
  > | - | - |
  > | **Native turn filler** | While Runtime works on a caller turn, OpenAI says a short hold phrase in the caller's language. Hold phrases stop when the answer is ready, never play during a transfer or handoff, and aren't added to the conversation. |
  > | **Filler prompt override** (Optional) | Replaces the default instruction OpenAI words each hold phrase from. Default: `Reply with a short, natural hold phrase in the current language.` Runtime appends fixed safety rules that prevent claims about results, actions, promises, questions, or tool calls. |
  >
  > **Advanced voice behaviour**
  >
  > | Field | Description |
  > | - | - |
  > | **Caller interruption** > **Let callers interrupt the agent** | When off, the caller speaking doesn't cut off what the agent is saying. |
  > | **Caller interruption** > **Protect non-interruptible outputs** | Uses model playback for protected outputs and protects the welcome unless interruption is allowed. Off by default. With server VAD, turning this on lets the model play protected outputs and protects the welcome unless `ON_START` allows interruption. An `ON_START` greeting authored with barge-in disallowed is protected automatically with server or semantic VAD, regardless of this switch. Input that repeats a protected output word for word is treated as echo. Menu answers, numbers, spelled names, and other caller input still run. |
  > | **Welcome interruption** | Allows callers to interrupt the initial welcome message. When disabled, the welcome message always plays to completion before the caller can interrupt. |
  > | **Silent caller reprompt** > **Reprompt a silent caller** | Uses the project's voice no-input settings (timeout, reprompt messages, retries, and final action) on this realtime channel. Turn it off to keep the channel silent. |
  > | **Caller transcript cross-check** > **Check the model's wording against the transcript** | Waits briefly for the caller's transcript and gives it to the agent beside what the model reported. |
  > | **Longest wait for the transcript (ms)** (Optional) | Sets how long the turn waits for the caller's transcript, up to 5000 ms. Leave empty to size the wait to the caller transcription model of the selected realtime model: 1500 ms for `whisper-1` and 400 ms for `gpt-4o` transcription. The turn runs without the transcript once the wait ends. |
  >
  > Also configure the **Advanced voice behaviour** settings that apply to all providers, described after the provider list.

* **Parallel caller transcription**: For supported Kore.ai Voice Gateway (KoreVG) realtime channels, you can use a separate speech-to-text (STT) provider to transcribe caller audio while the realtime speech-to-speech (S2S) provider handles the conversation. The S2S provider continues to supply the agent's response transcript.

* **Availability:** Off by default. A platform administrator must enable the **Realtime LLM parallel STT** feature for your tenant. When enabled, use the **Caller transcription** card on the **Speech** tab to select a configured STT provider instance and the caller's language.

* **Supported S2S providers:** **OpenAI Realtime**, **Azure OpenAI Realtime**, **Grok Realtime (S2S)**, and **Google Gemini Live**. **Amazon Nova Sonic (S2S)** isn't supported.

* **Transcripts:** Final transcripts from the STT provider are used for caller messages in the session transcript and conversation history, with one message per caller turn. Interim caller transcripts aren't sent. Agent transcripts still come from the S2S provider. If the STT provider doesn't return a final transcript within 3 seconds, the system falls back to the S2S caller transcript.

* **Troubleshooting:** The `voice_stt` trace can show both the STT transcript (`transcript`) and the S2S transcript (`s2sTranscript`) for the same caller turn. They're two values for one turn, not separate messages.

* **Billing:** Caller audio goes to both the STT provider and the S2S provider, so review usage and billing for both.

> [!NOTE]
>
> The existing **Caller wording** setting controls which wording the agent runs a caller turn on. Itsis separate from selecting an STT provider for caller transcription. If you don't see the **Caller transcription** card, ask your platform administrator whether the feature is enabled for your tenant. If the feature is revoked after configuration, the saved settings become read-only and new calls use S2S caller transcription.

* **Advanced voice behaviour (all providers)**: Optional behaviours for this channel. Each one is off, empty, or set to the earlier platform behaviour until you change it.

  | Field | Description |
  | - | - |
  | **Caller wording** > **Wording a caller turn runs on** | Select the wording the agent runs a caller turn on: **Model's wording** (default), **Auto: prefer the caller's transcript**, or **Caller transcript**. |
  | **Default transfer announcement** > **Line spoken before a transfer** (Optional) | The line the agent speaks before a transfer, for example `One moment while I connect you.` |
  | **Runtime-owned speech** > **Speak Runtime answers exactly** | Runtime makes the voice model say its answers word for word, once per caller turn, and records what was said. |
  | **Noise isolation** | Applies server-side noise reduction to inbound call audio to filter out background voices and ambient noise. |
  | **Trust inbound SIP headers** | The same setting as on the **Settings** tab. Off by default. Turn it on only if your SBC sets or overwrites these headers. |

* **Voice transfer and survey capabilities**: A read-only panel that shows how many of the transfer and survey capabilities Runtime evaluates as available for the concrete voice execution boundary (the execution surface is **KoreVG realtime S2S**), for example **11 of 11 capabilities available**. It lists the following capabilities, each marked **Available** or not.

  | Capability | Description |
  | - | - |
  | **Human transfer** | Transfer the caller to a human agent. |
  | **Pre-transfer announcement** | Speak an announcement before a transfer. |
  | **Transfer outcome recovery** | Recover when a transfer doesn't complete. |
  | **SIP transfer** | Transfer the call over SIP. |
  | **PSTN transfer** | Transfer the call to a phone number on the public telephone network. |
  | **Bridged agent transcript** | Carry the transcript to the agent the call is bridged to. |
  | **Transfer CSAT** | Collect a satisfaction rating after a transfer (`csat`, `nps`, `likeDislike`). |
  | **Template survey** | Run a template survey with a rating type of `star`, `thumbs`, or `scale`. |
  | **Survey comments** | Collect free-text comments in a survey. |
  | **Survey follow-ups** | Ask follow-up questions in a survey. |
  | **Return-leg survey** | Run a survey on the return leg of a transferred call. |

Click **Save Changes** on the **Speech** tab to apply the settings.

**7. Save and confirm provider readiness**

Resolve any missing provider credentials and model configuration before you test. After you save, confirm that Studio shows the phone number on the saved connection. Each tab has its own **Save Changes** button, so save on each tab you edit.
\[!WARNING] Don't repoint shared KoreVG or softphone hosts. Phone registration, device call, Jambonz API, and SBC hosts are shared environment settings. Only a connection-specific callback may target a local tunnel during isolated testing.

### Test and verify the channel

Open the **Testing** tab to verify the channel before going live.

* **Shareable softphone link:** Generate a time‑limited link that lets anyone call the channel from a phone browser through the real gateway and view a read‑only transcript.
  * Links expire after 7 days and can be revoked at any time.
  * **Active links** shows links currently in use, or **No active links for this channel**.
  * Viewing active links requires read access; generating or revoking links requires edit permission.

* **Soft Phone dialer:** From the **Settings** tab, select **Soft Phone > Launch dialer** to call the agent directly from your browser.
  * No DID purchase or telephony charges are required.

**Verify and secure the Realtime LLM Voice channel**

Before you go live, validate the quality of realtime calls. Realtime quality depends on the slowest leg of the call, so test each of the following.

**1. Preview with HTTPS voice**

Generate a time‑limited preview, allow microphone access, start and stop a call, mute/unmute, and confirm chat remains usable if microphone or provider setup fails.

**2. Run an isolated PSTN test call**

Dial the provisioned number and validate greeting, bidirectional audio, tool execution, transfer/termination, caller hang‑up, and one stable Runtime session.

**3. Measure latency budget**

Record gateway connect time, provider session setup, input audio commit, first model audio, end‑to‑end turn p50/p95, jitter, and packet loss.

**4. Test barge‑in and rapid turns**

Interrupt a long agent response, speak immediately, and verify stale audio is cancelled, tool calls aren’t duplicated, and the next user turn is preserved.

**5. Exercise failure scenarios**

Deny microphone access, force provider disconnect, gateway reconnect, model timeout, tool failure, phone hang‑up, and capacity rejection. Confirm caller hears or receives the designed fallback.

**Security, Latency, and Reliability Practices**

* **Protect credentials:** Treat realtime provider and carrier credentials as administrator‑managed secrets. Don't copy API keys into connection identifiers, browsers, screenshots, or agent prompts.
* **Minimize overhead:** Avoid unnecessary transcoding, buffering, proxy hops, and oversized tool responses. Set explicit connection and turn timeouts, and verify heartbeat behavior through every proxy.
* **Validate capacity:** Check provider concurrency, KoreVG session limits, phone capacity, and backpressure before load tests. Capacity rejection must fail predictably, not degrade active calls.
* **Define fallback behavior:** Specify caller‑visible handling for provider unavailability, timeout, safety rejection, tool failure, and transfer failure. Include rules for retry, reprompt, mode switch, or call termination.
* **Trace sessions:** Capture call/session IDs, provider events, tool calls, turn latency, interruptions, errors, and termination reasons. Scrub audio, transcripts, and credential data from logs.

### Manage an existing Realtime LLM Voice channel

Open a channel from **Deployments** > **Channels** > **Voice** > **Realtime LLM Voice** and select a connection. The connection header shows the display name, its status (for example, *Active*), and when it was last updated. The connection has three tabs.

| Tab | Description |
| - | - |
| **Settings** | The **Display Name**, **Realtime LLM Voice Settings** (**Provider Verification Strength**, **Voice Provider**, and **Call routing** or **SIP Configuration**), **Trust inbound SIP headers**, and **Connection Name**. Described in [Configure the Realtime LLM Voice channel](#configure-the-realtime-llm-voice-channel). |
| **Speech** | **Realtime orchestration**, **Semantic convergence**, the **S2S provider** and its settings, and **Advanced voice behaviour**. Described in step 5 of [Configure the Realtime LLM Voice channel](#configure-the-realtime-llm-voice-channel). |
| **Testing** | The shareable softphone link and active links. Described in [Test the Realtime LLM Voice channel](#test-the-realtime-llm-voice-channel). |

Changing settings on the **Settings** or **Speech** tab updates the live channel after you click **Save Changes**.

### Troubleshoot Realtime LLM Voice

* **Calls to the number fail:** an **Active** phone-routed connection without a provisioned number can't receive production PSTN calls. Assign or buy a number, and confirm it's bound to this connection.
* **The channel can't start a session:** resolve missing provider credentials and model configuration, then save the connection and test again.
* **Duplicate tool calls or stale audio after an interruption:** repeat the barge-in test from [Verify and secure the Realtime LLM Voice channel](#verify-and-secure-the-realtime-llm-voice-channel) and check the traces for the affected call and session IDs.
  For the full validation checklist, click **Setup instructions** on the Realtime LLM Voice channel page.

## Set up Pipeline Voice channel

Pipeline Voice is a voice channel that handles calls through separate speech-to-text (STT), LLM, and text-to-speech (TTS) stages, connected through Kore.ai Voice Gateway (KoreVG). Unlike Realtime LLM Voice, which uses a single speech-to-speech model, this pipeline lets you choose and configure the speech recognition (ASR) and speech synthesis (TTS) providers independently.

KoreVG captures the caller's speech through STT, sends the transcript to the deployed agent, and streams or plays the agent's response through TTS. Each stage has its own provider, latency, failure, and observability boundary.

> [!NOTE]
>
> Choose your voice provider before you begin. It determines which call routing fields apply later in this setup.

> [!TIP]
>
> Studio also provides in-product guidance. On the **Pipeline Voice** channel page, click **Setup instructions** to open a step-by-step panel that covers connection creation, speech pipeline and phone route configuration, validation of every voice phase, and security, queue, and reliability boundaries.

### Create a Pipeline Voice channel

To create a Pipeline Voice channel, go to **Deployments** > **Channels** > **Voice** > **Pipeline Voice** > **New connection** and complete the following steps in order.

**1. Set up the connection**

On the **New Pipeline Voice Connection** page, provide the following fields. The setup instructions appear alongside the form while you fill it in.

| Field | Description |
| - | - |
| **Display Name** | A label for the connection (up to 255 characters), for example `Pipeline Voice Production`. |
| **Connection Name** | A stable system name for the connection (up to 255 characters), such as `pipeline-voice-prod`. Use an environment-specific identifier. The connection name is separate from the phone number and the gateway account. |
| **Environment** | The deployment the connection binds to. Select an environment to follow its active deployment automatically, or leave the default to use the working copy. When no environment has an active deployment yet, create a deployment first to bind the connection to a published environment. You can change this later on the **Deployment** tab. |
| **Provider Verification Strength** | Controls how strictly the platform trusts the provider's identity assertions for session continuity and linking. **Weak** is the default. Choose **Strong** only for channels or providers whose identity assertions you trust for stronger continuity and linking decisions. |
| **Initial Status** | **Active** connections can be used immediately. **Inactive** connections stay saved but disabled until you activate them. |

**2. Create the connection**

Click **Create**. Create the connection before you configure the pipeline, because the saved connection owns the phone route and its STT, TTS, barge-in, no-input, and timeout configuration.

**Configure the channel**

Once the channel is created, open it from the **Pipeline Voice** connections list. The connection has four tabs:

* **Settings** holds the voice provider, call routing, and advanced voice behavior.
* **Speech** holds speech recognition, speech synthesis, and conversation controls.
* **Deployment** holds the environment binding.
* **Testing** holds the shareable softphone link.

> [!NOTE]
>
> Resolve missing STT and TTS credentials before you preview or activate the channel. Speech providers are administrator-configured credential sets. See [Voice Services](https://koreai.mintlify.site/agent-platform/administration/ai-configuration.md#voice-services).

**Configure the voice provider and call routing**

**1. Choose a voice provider**

On the **Settings** tab, under **Pipeline Voice Settings**, set **Voice Provider** to **Kore.ai Voice Gateway** or **Bring Your Own SIP**. Keep **Kore.ai Voice Gateway** selected unless your platform owner approves another route. KoreVG owns the Jambonz session, sticky gather, streaming TTS, interruption handling, and voice trace phases.

**2. Configure call routing (Kore.ai Voice Gateway)**

If you chose **Kore.ai Voice Gateway**, set the following under **Call routing**. Choose how calls reach this agent. Enable **Soft Phone** for browser testing, and add a phone number (DID) when the channel needs a real phone number.

| Route | Description |
| - | - |
| **Soft Phone** (Free) | Dial the agent from your browser. No DID purchase or telephony charges. Use this for evals, QA, and demos. Select **Launch dialer** to open the browser dialer. |
| **Phone Number (DID)** | Purchase a real phone number through Twilio. Disable this route to stop DID listing and call routing while keeping the number saved. |

> [!NOTE]
>
> If you enable **Phone Number (DID)**, complete the next step. If you chose **Bring Your Own SIP**, skip to step 4.

**3. Configure the phone number (DID only)**

Set the following fields, then select **Search Available Numbers** to list matching numbers. Verify that the number you buy or assign is bound to this connection before you activate it.

| Field | Description |
| - | - |
| **Provider** | The telephony provider, for example **Twilio**. |
| **Inbound calls** | Route calls from this number into the voice agent. |
| **Outbound calls** | Allow this number to be used for campaign dialout. |
| **Country** | The country of the number, for example **United States**. |
| **Number Type** | The type of number, for example **Local**. |
| **Area Code** (optional) | Filters the available local numbers by area code, for example `415`. |

Until the connection has a provisioned number, the channel header shows a **Needs phone provisioning** badge, and the page shows the warning **Configured without a phone number**. Assign or buy a number before you route phone calls.

**4. Configure SIP settings (Bring Your Own SIP only)**

If you chose **Bring Your Own SIP**, the **Call routing** options are replaced by a **SIP Configuration** section on the **Settings** tab. Set the following fields.

| Field | Description |
| - | - |
| **Our SIP Server Address** | A read-only address. Configure your SIP provider to send `INVITE` to this address, for example `korevg-np.kore.ai:5060`. Select **Copy** to copy the address. |
| **SIP Gateway IPs / CIDRs** | Provider SIP source addresses. Separate multiple IPv4 addresses or CIDR ranges with commas, for example `203.0.113.50:5080, 3.80.16.0/23`. |
| **SIP Termination URI** | The termination address your SIP provider expects outbound calls to reach. Select **IP Address** or **Domain Name**. For **IP Address**, enter up to 10 distinct IPv4 addresses separated by commas, for example `198.51.100.10, 198.51.100.11`. **Domain Name** accepts one domain name. Multiple IP addresses configure multiple destinations; they don't guarantee failover, which depends on your carrier or gateway. |
| **Port** | The port of the SIP termination address. Use the **−** and **+** buttons or type a value. The default depends on the selected transport. Change it to the carrier's port if different. |
| **Transport** | The protocol used to reach the carrier. See the following table. |
| **Gateway options** | Optional behaviors for the SIP trunk. The available options depend on the selected transport. See the following table. |
| **DID / Phone Number** | The phone number (DID) your SIP provider routes to this SIP gateway, for example `+14155551234` or `98492`. |

Select one of the following **Transport** options.

| Transport | Description |
| - | - |
| **UDP** | Default transport. The port defaults to `5060`. |
| **TLS** | SIP signaling over TLS. The port defaults to `5061`, the standard SIP over TLS port. The carrier must present a certificate that the voice gateway trusts. Media stays RTP unless you choose **TLS + SRTP**. |
| **TLS + SRTP (encrypted media)** | SIP signaling over TLS, with audio encrypted with SRTP for every call on this trunk. The port defaults to `5061`. The carrier must present a certificate that the voice gateway trusts. |

Under **Gateway options**, select the options that apply to your carrier.

| Option | Available for | Description |
| - | - | - |
| **Send OPTIONS ping** | All transports | Probes the endpoint and stops routing to it while it doesn't answer. |
| **Use sips: URI scheme** | TLS, TLS + SRTP | Sends `sips:` instead of `sip:` in the Request-URI. Turn it on only if the carrier requires it. |
| **Pad crypto** | TLS + SRTP | Pads SRTP crypto keys for carriers that reject unpadded keys. |
| **Remove ICE candidates** | TLS + SRTP | Strips ICE attributes from the SDP offer. |
| **Disable DTLS** | TLS + SRTP | Uses SDES keying only. |
| **Outbound calls** | All transports | Allows campaigns and dial-out to call through the SIP termination URI. |

> [!NOTE]
>
> Outbound calls need a SIP termination URI. Add one, or turn off **Outbound calls**. Otherwise, the platform rejects **Save Changes**.

Toggle **Enable E.164 (leading +)** to prepend a leading `+` to outbound numbers sent to the carrier. It's on by default, which international (full-E.164) numbers require. Turn it off only for local or national-format numbers, since the leading `+` otherwise misroutes them.

**5. Configure advanced voice behavior**

Under **Advanced voice behaviour**, set the optional behaviors for this connection. Select the section header to expand or collapse it. Each behavior is off, empty, or set to the earlier platform behavior until you change it.

| Field | Description |
| - | - |
| **Default transfer announcement** > **Line spoken before a transfer** (Optional) | The line the agent speaks before a transfer, for example `One moment while I connect you.` |
| **Connect greeting** (Audio) | Plays a clip as soon as the call connects, before the agent's first turn. If the project's greeting-audio library has no clips yet, the toggle is unavailable, and the panel shows the note **No greeting clips in this project library.** and an **Open Greeting Audio** link to add one. See [Greeting audio](https://koreai.mintlify.site/agent-platform/administration/general-settings.md#greeting-audio). |
| **Keypad tone** | Plays an audible keypad tone to the caller on each DTMF keypress. Off by default. |
| **Voice gateway turn detection** | Lets the voice gateway decide when the caller has finished speaking, using voice and wording signals instead of the speech provider's silence timer. Off by default. Requires a voice gateway that supports turn detection. |
| **Noise isolation** | Applies server-side noise reduction to inbound call audio to filter out background voices and ambient noise. |
| **Trust inbound SIP headers** | Off by default. Turn it on only if your SBC sets or overwrites these headers. If the headers can arrive from the caller, the value isn't trustworthy. When on, transfer headers configured to pass through from the inbound call (for example, `User-to-User`) are sent on the transfer. When off, they're dropped. |

> [!WARNING]
>
> Don't enable **Keypad tone** for PCI or secure-input flows until secure-input suppression is in place. Real keypad tones reproduce the entered digits in the recording.

When you turn on **Voice gateway turn detection**, set **Patience** to control how long the gateway waits before it decides the caller has finished speaking.

| Option | Use it for |
| - | - |
| **Fastest (0.3)** | The quickest replies. Most likely to cut off callers who pause mid-sentence. |
| **Fast (0.4)** | Quick replies for short answers. |
| **Balanced, recommended (0.5)** | General conversation. Default. |
| **Patient (0.6)** | Callers who pause while they think. |
| **Very patient (0.7)** | Spelled names, numbers, and long answers. |
| **Dictation (0.8)** | Waits through the long pauses of card numbers. |
| **Slow dictation (0.9)** | Waits longest. Use it for letter-by-letter spelling and long reference numbers. |

Faster settings reply sooner but may cut off callers who pause mid-sentence.

**Configure speech recognition**

On the **Speech** tab, under **Speech Recognition**, set the following fields. The available fields vary by provider.

| Field | Description |
| - | - |
| **Display Name** | The connection's display name. It's also editable on the **Settings** tab. |
| **Provider** | The speech-to-text credential set to use, for example `Deepgram Speech Credentials` or `Microsoft Speech Credentials`. |
| **Language** | The recognition language, for example `Multilingual` or `Afrikaans (South Africa)`. |
| **Alternative recognition languages** | Additional languages the recognizer can listen for. Select the languages from the list. |
| **STT Model** | For providers that offer model selection, the recognition model, for example `Nova 3 (latest, most accurate)`. Deepgram's managed defaults use 600 ms endpointing and 1,500 ms utterance-end behavior. |
| **Minimum STT confidence** | Rejects transcripts below this confidence (0-1) and treats them as no-input. `0` disables the gate. The value is provider-relative, so calibrate it per channel. |
| **Custom vocabulary** | Adds domain-specific terms to improve speech recognition. Select **Add phrase**, then enter the **Phrase** (for example `policy number`) and an optional **Boost**. Microsoft and Azure phrase lists are presence-based, so boost values are saved but ignored at runtime. For **Emotech**, add **hotwords** (domain-specific words or phrases you want the speech recognition system to recognize more reliably) and set the **Hotword Weight**. A value from 5 to 10 is recommended. Clear the custom vocabulary list to disable hotwords. |
| **Multilingual speech recognition** | Chooses the recognizer that listens for each configured language. Enable **A different recognizer per language** to select the configured speech recognizer that should listen after an explicit language change. |

To configure language-specific recognition, add a language profile first. A profile can contain speech synthesis, speech recognition, or both. Under **Language**, choose a language or enter a language tag (for example `en-US`), then select **Add language**.

**Configure speech synthesis**

Under **Speech Synthesis**, set the following fields. The available fields vary by provider.

| Field | Description |
| - | - |
| **Voices by language** | Select **A different voice per language** to give each language its own voice instead of one voice for every caller. When cleared, the channel uses a single TTS configuration for all callers. |
| **Provider** | The text-to-speech credential set to use, for example `ElevenLabs (TTS) Credentials`, `Deepgram Speech Credentials`, `Emotech (TTS) Credentials`, or `Microsoft Speech Credentials`. |
| **Language** | For providers that need it, the synthesis language, for example `ar-SA`. |
| **Voice** | The voice used for synthesized speech, for example `Sarah - Mature, Reassuring, Confident - (american, young, female)`. Some providers, such as Emotech, take the voice ID as text, for example `ar-SA_Male_3_Premium_beta`. |
| **Switch TTS for detected language** | When enabled, calls can change the TTS language, voice, and model after speech recognition detects a different language. |

> [!NOTE]
>
> * Use the provider's required language format. For example, ElevenLabs expects an ISO 639-1 code such as `en`, not `en-US`.
> * After you add a language, the platform creates a dedicated TTS configuration section for that language. Configure the provider, voice, model, and any provider-specific settings independently for each language.
> * Available fields vary by provider. Some providers expose additional settings such as TTS model, output format, speed, temperature, and voice tuning controls.

**Configure conversation controls**

Set the following fields to tune barge-in, listening mode, speech timeout, and no-input behavior for the caller experience.

| Field | Description |
| - | - |
| **Barge-in** | Allow the caller to interrupt the agent while it's speaking. |
| **Listening mode** | Controls how the call handles caller interruption. Select **Agent setting, else Barge-in (Turn-taking)** (default), **Background**, or **Turn-taking**. When no mode is set, the entry agent's listening setting decides, and without one the mode follows the **Barge-in** checkbox. Once you set a mode here, it takes priority over the agent's setting, and the **Barge-in** checkbox only sets the default for caller interruption. The mode is fixed for the whole call. See the following table. |
| **Stream speech** | Speaks each reply as it's generated, for a faster first word. When off, every reply, greeting, and reprompt plays only after it's fully generated. |
| **Speech Timeout (ms)** | Controls how long the speech provider waits through silence before finalizing the current speech segment. This doesn't combine separate final results. The allowed range depends on the provider (for Microsoft, 100-5000 ms). Leave blank to use the provider default, or select **Use recommended value (3000 ms)**. |
| **Transcript Grouping Timeout (ms)** | After the speech provider returns a final result, waits this long for another final result and combines the parts into one user input. Leave blank to process each final result immediately. For example, `1500`. |
| **Welcome Message** | The opening prompt the agent speaks, such as `Hello! How can I help you today?`. |
| **Allow caller to interrupt the welcome** | When off, the welcome plays to completion even if barge-in is on. It applies only while barge-in is active for the call, through the channel's **Barge-in** setting or the agent's listening settings. |

Select one of the following **Listening mode** options.

| Option | Description |
| - | - |
| **Agent setting, else Barge-in (Turn-taking)** | Default. Uses the entry agent's listening setting. Without one, the mode follows the **Barge-in** checkbox. |
| **Background** | The system actively listens while the agent is speaking, and the no-input timer pauses whenever caller speech is detected. |
| **Turn-taking** | A listener opens only after a prompt completes. Prompts play as complete audio rather than streamed content. |

> [!NOTE]
>
> If you pair **Background** with **Barge-in** off, it behaves like a slower **Turn-taking** mode, and Studio displays a warning.

**Voice transfer and survey capabilities**

A read-only panel shows how many of the transfer and survey capabilities Runtime evaluates as available for the concrete voice execution boundary (the execution surface is **KoreVG pipeline**), for example **11 of 11 capabilities available**. It lists the following capabilities, each marked **Available** or not.

| Capability | Description |
| - | - |
| **Human transfer** | Transfer the caller to a human agent. |
| **Pre-transfer announcement** | Speak an announcement before a transfer. |
| **Transfer outcome recovery** | Recover when a transfer doesn't complete. |
| **SIP transfer** | Transfer the call over SIP. |
| **PSTN transfer** | Transfer the call to a phone number on the public telephone network. |
| **Bridged agent transcript** | Carry the transcript to the agent the call is bridged to. |
| **Transfer CSAT** | Collect a satisfaction rating after a transfer (`csat`, `nps`, `likeDislike`). |
| **Template survey** | Run a template survey with a rating type of `star`, `thumbs`, or `scale`. |
| **Survey comments** | Collect free-text comments in a survey. |
| **Survey follow-ups** | Ask follow-up questions in a survey. |
| **Return-leg survey** | Run a survey on the return leg of a transferred call. |

**Bind the channel to an environment**

On the **Deployment** tab, under **Environment Binding**, use the **Environment** dropdown to select which deployed version handles incoming messages.

| Option | Description |
| - | - |
| **Working Copy (draft)** | Uses the current draft of the project. |
| **Development**, **Staging**, **Production** | Uses the active deployment of that environment. An environment with no active deployment appears dimmed with **(no active deployment)** and can't be selected. |

Click **Save Changes** to apply the binding. The button is available only after you change the environment.

**Save the configuration**

Click **Save Changes** to apply the configuration. Each tab has its own **Save Changes** button, so save on each tab you edit. Confirm the selected deployment, phone number, locale, voices, and timeouts before you activate the channel.

> [!NOTE]
>
> If saving shows the warning **Voice gateway synchronization is incomplete. Your configuration is saved; retry Save after the gateway recovers.**, the platform saved your settings but couldn't sync them to the voice gateway. Click **Save Changes** again after the gateway recovers.

### Test and verify the channel

Open the **Testing** tab to test the channel before you go live.

Under **Shareable softphone link**, select **Generate link** to create a link that lets anyone with the link call this channel from a phone browser through the real phone gateway and see a live, read-only transcript. Links expire after 7 days, and you can revoke them at any time. **Active links** lists the links currently in use, or shows **No active links for this channel.** You can view active links with read access. Generating or revoking links needs permission to edit the channel.

You can also use **Soft Phone** > **Launch dialer** on the **Settings** tab to call the agent from your browser with no DID purchase or telephony charges.

**Verify and secure the installation**

Before you go live, validate every phase of the voice pipeline.

**1. Run the HTTPS preview**

Grant microphone access, start and stop a call, mute and unmute, and verify that the experience fails clearly if either speech provider is unavailable.

**2. Place a live phone call**

Through the provisioned number, validate the greeting, STT transcript accuracy, agent response, TTS playback, barge-in, tools, transfer or hang-up, and session continuity.

**3. Measure STT, LLM, TTS, and full-turn latency**

Record the STT first partial and final result, the agent's first token and completion, TTS stream open and first audio, full-turn p50 and p95, jitter, packet loss, and provider errors.

**4. Exercise silence and interruption**

Test silence through every no-input retry, short utterances near endpointing thresholds, speech during prompts, repeated barge-in, and rapid turns without duplicate execution.

**5. Test independent phase failures**

Disconnect STT, fail the agent model or a tool, reject TTS, exhaust capacity, and interrupt the network. Confirm that each phase produces the authored fallback and a clear trace.

> [!WARNING]
>
> Don't point shared softphone registration, device call, Jambonz API, or SBC hosts at a local machine. Shared telephony endpoints stay on the environment. Local testing may change only a dedicated connection callback.

Follow these security and reliability practices:

* Treat STT, TTS, carrier, and gateway credentials as administrator-managed secrets. Keep provider keys out of connection identifiers, browsers, agent prompts, and screenshots.
* Set explicit phase and turn latency budgets. Avoid unnecessary transcoding and buffering, and keep prompts, tool output, and synthesis chunks small for fast first audio.
* KoreVG processes each session sequentially through a bounded queue. Load-test rapid turns and concurrent calls to confirm that backpressure delays or rejects calls predictably.
* Define what the caller hears for low-confidence or empty STT, model or tool failure, TTS rejection, no-input exhaustion, transfer failure, and gateway disconnect.
* Capture scrubbed `voice_stt`, `voice_tts`, and `voice_turn` traces. Include call and session IDs, phase latency, interruptions, errors, provider names, cache state, and termination reasons.

### Manage an existing Pipeline Voice channel

Open a channel from **Deployments** > **Channels** > **Voice** > **Pipeline Voice**.

The connection has four tabs.

| Tab | Use it to |
| - | - |
| **Settings** | Set the voice provider, call routing (Kore.ai Voice Gateway) or SIP configuration (Bring Your Own SIP), and advanced voice behavior. Copy the connection identifiers. |
| **Speech** | Configure how the channel listens and speaks: speech recognition, speech synthesis, and conversation controls. |
| **Deployment** | Choose which environment handles incoming calls, either the working copy or a deployed environment, and view the **Active Deployment** it currently runs. |
| **Testing** | Generate a shareable softphone link to test the channel from a browser, and view or revoke active links. |

Changing settings on the **Settings**, **Speech**, or **Deployment** tab updates the live channel after you click **Save Changes**.

At the bottom of the **Settings** tab, the following identifiers are available. Select the copy icon to copy a value.

| Field | Description |
| - | - |
| **Voice Channel Connection ID** | The unique ID of the voice connection. Use this value as the `channelConnectionId` when you place an Outbound Dial API call. |
| **Webhook URL** | (Bring Your Own SIP only) The webhook endpoint for the connection, for example `https://<host>/api/v1/channels/voice_pipeline/byoc_sip/webhook`. |
| **Connection Name** | The system name of the connection. |

**Review recommended voice defaults**

When the project mixes voice and non-voice channels and the recommended voice defaults aren't active, the **Settings** tab shows the banner **Recommended voice defaults aren't active**. Review the voice-scoped profile. Non-voice sessions aren't changed. Select **Review voice defaults** to review the profile, or **Dismiss** to hide the banner. For details on the profile, see [Voice low-latency profile](https://koreai.mintlify.site/agent-platform/administration/general-settings.md#voice-low-latency-profile).

### Troubleshooting

* **Needs phone provisioning:** the connection has no phone number. Assign or buy a number under **Call routing** on the **Settings** tab before you route phone calls. A phone-routed connection can't be activated until it has a provisioned number.
* **Voice gateway synchronization is incomplete:** the platform saved your configuration but couldn't sync it to the voice gateway. Click **Save Changes** again after the gateway recovers.
* **Save is rejected on a Bring Your Own SIP connection:** **Outbound calls** is on but no SIP termination URI is set. Add a SIP termination IP address or domain name, or turn off **Outbound calls**.
* **Speech doesn't work or the preview fails:** confirm that both the STT and TTS providers have credentials configured, then save the connection before you preview or activate it.
* **No voice for a language:** use the provider's required language format. ElevenLabs expects an ISO 639-1 code such as `en`, not `en-US`.
* **Caller is cut off mid-sentence:** raise **Patience** under **Voice gateway turn detection**, or increase **Speech Timeout (ms)** and **Transcript Grouping Timeout (ms)**.
  For the full validation checklist, click **Setup instructions** on the Pipeline Voice channel page.

## Pipeline vs. realtime voice

Pipeline voice (speech-to-text, agent, text-to-speech) and Realtime LLM Voice (speech-to-speech) build the agent's turn differently underneath the same ABL. Knowing which one a channel uses matters when authoring instructions, reasoning about history after a handoff, or sizing tool results.

| | Pipeline voice | Realtime speech-to-speech |
| - | - | - |
| **System prompt** | The same chat prompt, plus `## Response Format (Voice Channel)`, `## Voice Delivery Instructions`, and the voice language policy | The same agent prompt and tools, plus a realtime operating section |
| **History** | The same history and compaction rules as chat | The provider holds the call's history itself. No history is sent on first connect. |
| **After a handoff** | The receiving agent sees history the same way chat does | Depends on the provider -- see below |
| **Tool results** | The same shaping and compaction as chat | Capped at 102,400 bytes, 8 levels deep, 64 keys per object, 128 array items, and 32,768 characters per string |

Handoff replay on realtime channels varies by provider. OpenAI Realtime and Azure OpenAI Realtime resend the new agent's prompt with a replay of up to 8 recent messages (4,000 characters total, 700 per message). Amazon Nova Sonic opens a new stream with recent turns in a short block (also up to 4,000 characters, 700 per message). Grok Realtime replays every earlier caller utterance. Gemini Live starts a fresh session and replays history.

### Authoring voice behavior in ABL

The Studio settings on this page configure a channel. The agent's own spoken behavior is authored in ABL:

* **Spoken-style rules and grounding guards** -- `EXECUTION.voice.instructions` and `EXECUTION.voice.grounding_guards`, which replace the platform's default voice formatting rules and can refuse ungrounded tool arguments or figures. See [Voice instructions and grounding guards](https://koreai.mintlify.site/agent-platform/abl-reference/agent-declaration.md#voice-instructions-and-grounding-guards).
* **Realtime delivery tone** -- `EXECUTION.voice.coordinator_policy` (tone, pace, brevity, interruption handling, accessibility read-backs). See [Voice coordinator policy](https://koreai.mintlify.site/agent-platform/abl-reference/agent-declaration.md#voice-coordinator-policy).
* **Per-response voice overrides** -- the `VOICE:` block on a `RESPOND` (SSML, plain text, provider, voice, speed) plus the step- and response-scoped `BARGE_IN`, `STREAMING`, and `END_OF_SPEECH_TURN_TYPE` overrides. See [Voice configuration](https://koreai.mintlify.site/agent-platform/abl-reference/rich-content.md#voice-configuration) and [Scoped barge-in](https://koreai.mintlify.site/agent-platform/abl-reference/flow.md#scoped-barge-in).
* **Listening and turn-taking** -- `CONVERSATION: listening:` (barge-in, no-input retries, caller backchannel, on-hold phrases, barge-in continuation merging). See [Voice turn-taking](https://koreai.mintlify.site/agent-platform/abl-reference/behavior-profiles.md#voice-turn-taking).
* **Low-latency defaults** -- new projects and voice channels get the `customer_service_voice_low_latency_v1` profile automatically: tighter compaction, the fast model tier for every operation, reasoning off, and inline gather on. The Studio side of this profile -- model routing, compaction budgets, and filler tuning -- is covered in [Voice low-latency profile](https://koreai.mintlify.site/agent-platform/administration/general-settings.md#voice-low-latency-profile).

> [!WARNING]
>
> The low-latency profile doesn't fall back to the project's default model. If the workspace has no model assigned to the fast tier, voice turns have no model to call.

```yaml theme={null}
EXECUTION:
  voice:
    instructions: "Speak warmly in plain sentences. No lists. One or two short sentences per answer."
    grounding_guards:
      tool_arguments: true
      reply_figures: true
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.