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.

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.

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.

Create the connection

Click Create.

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.

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.

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.

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

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.

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, as either an IP Address or Domain Name. Select the type, then type the SIP termination IP address or domain name in the SIP termination URI field below it.
DID / Phone Number	The phone number (DID) your SIP provider routes to this SIP gateway.
Enable E.164 (leading +)	Prepend a leading `+` to outbound numbers sent to the carrier. On by default, which international (full-E.164) numbers require. Turn off only for local or national-format numbers, otherwise the leading `+` misroutes them.

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 are dropped.
Connection Name	The system name of the connection. Select the copy icon to copy it.

Click Save Changes to apply the settings.

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.

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.

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, then add it to the 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.

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

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 fillersTurn 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 fillerTurn 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 (Nova-specific)

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.

Also configure the Advanced voice behaviour settings that apply to all providers, described after the provider list.

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.

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.

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 fillerSeparate 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 safeguardsShared 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 detectionControls 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 does not respond within 8 seconds, the Gemini session restarts with the caller’s words, without re-prompting tool results.

Advanced voice behaviour (Gemini-specific)

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.

OpenAI Realtime

Under OpenAI Realtime Configuration, set the following fields.

Field	Description
Voice	The voice used to speak to callers. Default: Marin (recommended).

Turn detectionTune 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`.

Caller transcriptionHow 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.

Never put a caller’s own details in Words to expect. The transcriber would then hear them from anyone.

Realtime turn fillerApplies 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 (OpenAI-specific)

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.
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.

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.

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.

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 the Realtime LLM Voice 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.

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.

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.

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.

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.

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. Do not 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.
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.
Testing	The shareable softphone link and active links. Described in 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 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

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

Choose your voice provider before you begin - it determines which additional fields apply later in this setup.

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

Set Up the Connection

On the New Pipeline Voice Connection page, provide the following fields.

Field	Description
Display Name	A label for the connection.
Connection Name	A system name for the connection, such as `pipeline-voice-prod`. Up to 255 characters.
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.
Provider Verification Strength	Controls how strictly the platform trusts the provider’s identity assertions for session continuity and linking. Weak is set by default. Choose Strong only for channels/providers whose identity assertions you trust for stronger continuity and linking decisions.
Initial Status	Active connections are usable immediately. Inactive connections stay saved but disabled until you activate them.

Click Create.

Choose a Voice Provider

After creating the channel, go to the Configuration tab. Under Pipeline Voice Settings, set Voice Provider to either Kore.ai Voice Gateway or Bring Your Own SIP — this determines which call routing fields appear next.

Configure Call Routing (Kore.ai Voice Gateway)

If you chose Kore.ai Voice Gateway, set the following fields under Call routing. Choose how calls reach this agent — enable Soft Phone for browser testing, or add a DID when this 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.

If you enable Phone Number (DID), complete the next step. If you chose Voice Provider: Bring Your Own SIP instead, skip to Configure SIP Settings.

Configure the Phone Number (DID Only)

Set the Provider to Twilio, toggle Inbound calls (route calls from this number into the voice agent) and Outbound calls (allow this number to be used for campaign dialout), and select a Country and Number Type. Optionally enter an Area Code to filter available local numbers. Select Search Available Numbers to list matching numbers.

Configure SIP Settings (Bring Your Own SIP)

If you chose Voice Provider: Bring Your Own SIP, set the following fields under SIP Configuration.

Field	Description
Our SIP Server 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, as either an IP Address or Domain Name. Enter the URI in the field below the selected type.
DID / Phone Number	The phone number (DID) your SIP provider routes to this SIP gateway, for example `+14155551234` or `98492`.

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

Connect greeting

Plays the configured as soon as the call connects. Configure greeting audio under Runtime config settings.

Keypad tone

Plays an audible keypad tone to the caller each time a DTMF key is pressed. Disabled by default. Do not enable this setting for PCI or secure-input flows until unit testing confirms that keypad tones are not included in call recordings.

Voice gateway turn detection

Allows the voice gateway to determine when the caller has finished speaking using voice and wording signals instead of the speech provider’s silence timer. Disabled by default.

Requires a voice gateway that supports turn detection.

Patience: Specifies how long the voice gateway waits for the caller to finish speaking before determining that the turn is complete. The available options balance response speed with tolerance for pauses while the caller is speaking or spelling information.

Faster settings respond sooner but may interrupt callers who pause mid-sentence.
More patient settings wait longer and are better suited for spelled names, numbers, and longer answers.
Slow waits the longest and is suitable for letter-by-letter spelling and long reference numbers.

Trust inbound SIP headers

Specifies whether to trust SIP headers received from the inbound call. Enable this setting only if your SBC sets or overwrites these headers. If the headers can originate from the caller, their values are not trustworthy. When enabled, headers configured to pass through from the inbound call (for example, User-to-User) are sent on the transfer. When disabled, these headers are dropped.

Configure Speech Recognition

Under Speech Recognition, set the following fields.

Field	Description
Provider	The speech-to-text credential set to use, for example `Deepgram Speech Credentials`.
Language	The recognition language, for example `Multilingual`.
STT Model	The recognition model, for example `Nova 3 (latest, most accurate)`.
Minimum STT confidence	Reject transcripts below this confidence (0-1) and treat them as no-input. `0` disables the gate. Provider-relative - calibrate per channel.
Custom vocabulary	Add domain-specific terms to improve speech recognition. You can set the Phrase (for example `ACME, policy number`) and optional Boost. 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	Choose the recognizer for each configured language. Enable A different recognizer per language to select the speech recognizer for each language. Add a language profile before configuring language-specific recognition.

Configure Speech Synthesis

Under Speech Synthesis, set the following fields.

Field	Description
Voices by language	Enable this option to configure separate text-to-speech settings for each language supported by the agent. When disabled, the channel uses a single TTS configuration for all languages.
Language	Select the language for which you want to create a TTS profile, then click Add language.
Provider	The text-to-speech credential set to use for the selected language, for example `ElevenLabs (TTS) Credentials` or `Deepgram Speech Credentials`.
Voice	The voice used for synthesized speech for the selected language, for example `Sarah - Mature, Reassuring, Confident - (american, young, female)`.
Switch TTS for detected language	When enabled, calls can change the TTS language, voice, and model after speech recognition detects a different language.

After you click Add 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. Each language profile maintains its own provider configuration, allowing multilingual agents to use different voices and models for different languages.

Tune ElevenLabs Voice Settings (ElevenLabs Only)

If you selected an ElevenLabs voice, override playback and prosody for this channel connection under ElevenLabs Voice Settings.

Field	Description
TTS Model	The synthesis model, for example `Eleven Multilingual v2`.
Speed	Adjusts speaking pace. `1.0` is normal; lower slows the voice down, higher makes it faster. Range: `0.7`–`1.2`.
Stability	Controls consistency across generations. Higher is more stable and less expressive; lower allows more variation. Range: `0`–`1`.
Similarity boost	Keeps the output closer to the selected voice. Higher values preserve more of the original voice character. Range: `0`–`1`.
Style exaggeration	Amplifies voice style and emotion. Higher values can sound more expressive but may increase latency or instability. Range: `0`–`1`.
Speaker boost	Enhances speaker similarity and clarity. Turning it off may reduce latency for some voices.

Under Preview Voice, enter sample text (up to 500 characters) and select Generate to hear the configured voice before saving.

Configure Conversation Controls

Set the following fields.

Field	Description
Barge-in	Allow the caller to interrupt the agent while it is speaking.
Speech Timeout (ms)	Controls how long the speech provider waits through silence before finalizing the current speech segment. This does not combine separate final results. For example, `3000`.
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	Allows callers to interrupt the welcome message when barge-in is active.
Noise isolation	Apply server-side noise reduction to inbound call audio to filter out background voices and ambient noise.

Under Connect greeting (audio), optionally play 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 panel shows a note and an Open Greeting Audio link to add one.

Save the Channel

Click Save Changes to apply the configuration.

Manage an existing Pipeline Voice channel

Open a channel from Deployments > Channels > Voice > Pipeline Voice. It displays the following three tabs.

Overview
Configuration
Deployment

The Connection Summary displays these fields.

Field	Description
Status	for example: Active
Created	Timestamp the channel was created
Updated	Timestamp of the last change
Environment	for example: `dev`
Source Type	`Channel Connection`
Source ID	Unique identifier (UUID) of the channel

The Deployment tab displays these fields.

Field	Description
Agent Version	An Environment menu (for example: `Development`) that selects which deployed version handles incoming messages.
Active Deployment	Displays the bound deployment version and when it was deployed.

Click Save Changes after switching the environment or the version.

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.
Realtime delivery tone — EXECUTION.voice.coordinator_policy (tone, pace, brevity, interruption handling, accessibility read-backs). See 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 and 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.
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.

The low-latency profile does not 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.

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

Get started

Build

Test and evaluate

Deploy

Analytics and insights

References

Set up Realtime LLM Voice channel

Create a Realtime LLM Voice channel

Configure the Realtime LLM Voice channel

Test the Realtime LLM Voice Channel

Verify and secure the Realtime LLM Voice channel

Security, Latency, and Reliability Practices

Manage an existing Realtime LLM Voice channel

Troubleshoot Realtime LLM Voice

Set up Pipeline Voice channel

Manage an existing Pipeline Voice channel

Pipeline vs. realtime voice

Authoring voice behavior in ABL

​Set up Realtime LLM Voice channel

​Create a Realtime LLM Voice channel

​Configure the Realtime LLM Voice channel

​Test the Realtime LLM Voice Channel

​Verify and secure the Realtime LLM Voice channel

​Security, Latency, and Reliability Practices

​Manage an existing Realtime LLM Voice channel

​Troubleshoot Realtime LLM Voice

​Set up Pipeline Voice channel

​Manage an existing Pipeline Voice channel

​Pipeline vs. realtime voice

​Authoring voice behavior in ABL

Set up Realtime LLM Voice channel

Create a Realtime LLM Voice channel

Configure the Realtime LLM Voice channel

Test the Realtime LLM Voice Channel

Verify and secure the Realtime LLM Voice channel

Security, Latency, and Reliability Practices

Manage an existing Realtime LLM Voice channel

Troubleshoot Realtime LLM Voice

Set up Pipeline Voice channel

Manage an existing Pipeline Voice channel

Pipeline vs. realtime voice

Authoring voice behavior in ABL