referenceFree

livekit-translation-demo

Local Next.js 16 demo for a LiveKit video room with per-listener OpenAI

LiveKit Realtime Translation Demo

Local Next.js 16 demo for a LiveKit video room with per-listener OpenAI Realtime Translation. LiveKit carries browser-to-browser camera and microphone media. Each browser translates subscribed remote microphone tracks through an OpenAI WebRTC connection and keeps captions/transcripts in local React state.

Setup

Create .env in this demo folder:

LIVEKIT_API_KEY=
LIVEKIT_API_SECRET=
LIVEKIT_URL=
OPENAI_API_KEY=
OPENAI_TRANSLATION_MODEL=gpt-realtime-translate

OPENAI_TRANSLATION_MODEL is optional and defaults to gpt-realtime-translate.

Run

From the cookbook repo root:

cd examples/voice_solutions/realtime_translation_guide/livekit-translation-demo
pnpm install
pnpm dev

Open the local URL printed by Next.js. Use the same meeting code in two browser windows to join the same LiveKit room.

Validation

From the cookbook repo root:

cd examples/voice_solutions/realtime_translation_guide/livekit-translation-demo
pnpm test
pnpm lint
pnpm typecheck
pnpm build

The OpenAI translation payload tests cover the translation client secret request, the translation WebRTC call endpoint, session.audio.output.language, optional input transcription, and optional near-field noise reduction.

Related skills.

AmazonBedrock

This course is intended to provide you with a comprehensive step-by-step understanding of how to engineer optimal prompts within Claude, using Bedrock.

anthropic_api_fundamentals

A series of notebook tutorials that cover the essentials of working with Claude models and the Anthropic SDK including:

bootstrap-realtime-eval

Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtime_evals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval in this repository.