The outcome

Handle inbound or outbound calls without silent recording, uncontrolled dialing, identity abuse, or irreversible tool execution.

LiveKit is a Open-source realtime framework and cloud platform for voice, video, text, telephony, and multimodal AI agents. Building low-latency voice assistants, multimodal room participants, phone agents, realtime translation, tool-using conversational workflows, and human handoffs. This guide narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Document allowed numbers, regions, hours, consent law, caller ID, disclosure script, recording policy, opt-out, rate, budget, abuse limits, and escalation ownership.

  2. 02

    Separate SIP, LiveKit, and model secrets, authenticate dispatch, allowlist destinations, cap concurrent calls and duration, and prevent user speech from changing system routing or tool policy.

  3. 03

    Instrument connection, audio, transcription, turn, model, synthesis, tool, transfer, cost, and disconnect events while redacting sensitive content and setting explicit retention.

  4. 04

    Rehearse voicemail, answering machines, wrong parties, emergency language, fraud, harassment, payment data, provider outage, audio loss, duplicate dialing, and warm-transfer failure.

  5. 05

    Launch behind a kill switch and human supervisor, sample calls only with proper notice, reconcile dial and tool logs, block abuse quickly, and expand regions or actions only after review.

Working standard

What good use looks like.

  • Allowlist destinations and cap concurrency.
  • Separate routing from conversation text.
  • Maintain a human kill switch.

Realtime agents can hear, transcribe, infer, speak, call tools, and initiate telephony actions before a reviewer can intervene. Hidden observation, recording, voice cloning, payment or identity collection, and cross-provider routing carry serious consent and privacy risk. LiveKit Inference is zero-data-retention by default, but plugins, observability, recordings, telephony, and external models have separate policies. Require clear disclosure, least-privilege tools, explicit confirmation, human handoff, and an immediate kill switch.

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this collection.