# openai/openai-realtime-api-beta

Node.js + JavaScript reference client for the Realtime API (beta)

Repository: https://github.com/openai/openai-realtime-api-beta
Canonical: https://ross.abutalabs.com/products/openai-realtime-api-beta
Language: JavaScript
License: MIT
License Family: permissive
Topics: javascript, nodejs, openai, typescript
Last push: 2024-11-07T22:51:02+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 50
- inputs: {"age_days": 702, "days_push": 664, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1016, forks 288 (observed 2026-08-28T04:03:14.522951+00:00)

## What it is
A Node.js and browser reference client library for OpenAI's Realtime API, enabling real-time voice and text conversations with GPT models. It supports session configuration, streaming audio, tool use, and conversation event handling in JavaScript and TypeScript.

## Use cases
- build a realtime voice chatbot with openai
- stream audio to gpt for live conversation
- prototype a conversational voice assistant in node.js
- add speech-to-speech conversation to a react app
- connect to openai realtime api with websockets
- build an ai voice agent with tool calling

## When to choose
- you want to prototype realtime voice/text conversations with OpenAI models quickly
- you need a lightweight client for the Realtime API in Node.js or browser apps
- you want reference code showing session config, audio streaming, and tool use

## When to avoid
- you need a production-stable SDK - this is explicitly beta and superseded by the official OpenAI SDK
- you use a language other than JavaScript/TypeScript
- you want to ship API keys in browser code without a relay server

## Facets
- artifact type: library
- maturity: experimental
- function: sdk, http-client, websocket, speech-recognition, tts, chatbot
- domain: large-language-models, artificial-intelligence, speech-processing, chatbots, developer-tools
- platform: browser, cross-platform
- tags: openai, realtime-api, voice-assistant, beta, reference-client, conversational-ai, audio-streaming, nodejs, javascript

## Member repositories
- openai/openai-realtime-api-beta (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:14.522951+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:11:20.149315+00:00, confidence not recorded.
  - readme: https://github.com/openai/openai-realtime-api-beta (fetched 2026-08-28T04:03:14.522951+00:00, sha ec80ef9188aa)
- Data as of 2026-08-30T08:39:29.467469+00:00.