How to use
LiveKit.

1. 01

   Start at https://livekit.io/ and confirm the domain before entering account or payment information.

2. 02

   Availability: LiveKit Agents is available through Python and Node.js SDKs, a browser-based Agent Builder and console, LiveKit Cloud deployment and inference, or self-hosted LiveKit infrastructure.

3. 03

   A supported development environment or cloud project, secure LiveKit and model credentials, authorized voice and telephony data, latency and interruption testing, consent, observability controls, and a human escalation path.

4. 04

   Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

5. 05

   Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

• Use official download pages.
• Review permissions during setup.
• Keep installers and applications updated.

1. 01

   Define the caller, purpose, allowed topics, identity disclosure, languages, latency, interruption behavior, tools, consent, recording, retention, accessibility, and human handoff.

2. 02

   Prototype with minimum synthetic data and the simplest STT-LLM-TTS or realtime pipeline, keeping credentials server-side and every tool read-only or sandboxed.

3. 03

   Test noisy audio, silence, accents, crosstalk, barge-in, hallucination, unsafe requests, tool failures, latency, disconnection, and escalation while capturing approved metrics.

4. 04

   Add authentication, authorization, disclosure, redaction, rate and spend limits, monitoring, emergency stop, and human review before a narrow production canary.

• State the outcome before the background.
• Provide the real source material.
• Review the result before expanding the task.

1. 01

   Restate the brief, the deliverable format, and where the asset will appear before judging any output.

2. 02

   Inspect at full resolution: generated media hides its errors at thumbnail size.

3. 03

   Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.

4. 04

   Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.

5. 05

   Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.

• Inspect at full resolution before approving anything.
• Confirm commercial-use rights before an asset reaches a client.
• Keep the prompt and settings with the asset so it can be reproduced.

1. 01

   Confirm you hold the rights to every reference image, voice, or clip before uploading it.

2. 02

   Check whether your plan trains on submitted content, and opt out before uploading client work.

3. 03

   Never upload a real person's likeness or voice without their explicit, documented consent.

4. 04

   Review the output for marks, styles, or likenesses you have no licence to reproduce.

5. 05

   Label synthetic media where your client, platform, or jurisdiction requires disclosure.

• 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.
• Follow your organisation's approved-use policy.
• Never treat fluent output as authorization to act.

• LiveKit Agents introduction ↗
• Voice AI quickstart ↗
• LiveKit model overview ↗
• LiveKit Agent Console privacy ↗

Working on something like this? See how we handle brand identity, or book a call.