OpenAI

OpenAI Realtime API

The Realtime API from OpenAI — 9 operation(s) for realtime.

GitHub OpenAPI

Operations 9

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /realtime/calls Start a realtime voice call over WebRTC · Create call #
Ask an LLM
“How do I connect a browser to a realtime voice session over WebRTC?”
“Where do I send my SDP offer to get an answer back for a realtime call?”
Tell an agent
Start a WebRTC realtime call with SDP offer {sdp}.
Open a realtime call using offer {sdp} and session config {session}.
POST /realtime/calls/{call_id}/accept Accept an incoming SIP call · Accept call #
Ask an LLM
“When a phone call comes in over SIP, how do I answer it with a realtime model?”
“Can I set instructions and the model at the moment I pick up an incoming call?”
Tell an agent
Accept incoming call {call_id} as a {type} session.
Answer SIP call {call_id} as a {type} session on model {model} with instructions {instructions}.
POST /realtime/calls/{call_id}/hangup Hang up an active realtime call · Hang up call #
Ask an LLM
“How do I end a live realtime call from my server?”
“Can I hang up a call whether it came in over SIP or WebRTC?”
Tell an agent destructive · confirm first
Hang up call {call_id}.
End the active realtime call {call_id} now.
POST /realtime/calls/{call_id}/refer Transfer a SIP call to another destination · Refer call #
Ask an LLM
“Can I transfer a caller from the voice agent to a human's phone line?”
“How do I forward an active SIP call somewhere else?”
Tell an agent
Transfer call {call_id} to {target_uri}.
Forward the SIP call {call_id} to destination {target_uri}.
POST /realtime/calls/{call_id}/reject Decline an incoming SIP call · Reject call #
Ask an LLM
“Can I refuse an incoming phone call instead of answering it?”
“What SIP status code is sent when I decline a call without choosing one?”
Tell an agent destructive · confirm first
Reject incoming call {call_id}.
Decline call {call_id} with SIP status code {status_code}.
POST /realtime/client_secrets Create a short-lived realtime client secret · Create client secret #
Ask an LLM
“How can my web or mobile app talk to the realtime model without exposing my API key?”
“Can I control how long a realtime client secret stays valid?”
Tell an agent
Create a realtime client secret for session config {session}.
Mint a realtime client secret that expires after {expires_after}.
POST /realtime/sessions Create an ephemeral realtime session token · Create session #
Ask an LLM
“Can I preconfigure voice, instructions and tools when creating a realtime session token?”
“What's the session endpoint that returns an ephemeral key for client-side realtime use?”
Tell an agent
Create a realtime session with client secret settings {client_secret}.
Create a realtime session using voice {voice} and instructions {instructions}, with client secret settings {client_secret}.
POST /realtime/transcription_sessions Create a realtime transcription session · Create transcription session #
Ask an LLM
“How do I set up live speech-to-text streaming from a client app?”
“Can I turn on noise reduction for a realtime transcription session?”
Tell an agent
Create a realtime transcription session.
Start a live transcription session with transcription settings {input_audio_transcription}.
POST /realtime/translations/client_secrets Create a realtime translation client secret · Create translation client secret #
Ask an LLM
“How do I let a client app do live speech translation securely?”
“Can I set how long a realtime translation client secret lasts?”
Tell an agent
Create a realtime translation client secret for translation session {session}.
Mint a translation client secret for {session} that expires after {expires_after}.

Documentation

📖
Documentation
https://platform.openai.com/docs/assistants/overview
📖
Documentation
https://platform.openai.com/docs/api-reference/assistants
📖
Documentation
https://platform.openai.com/docs/guides/text-to-speech
📖
Documentation
https://platform.openai.com/docs/api-reference/audio
📖
Documentation
https://platform.openai.com/docs/guides/speech-to-text
📖
Documentation
https://developers.openai.com/api/docs/guides/audio/
📖
Documentation
https://developers.openai.com/api/docs/guides/voice-agents/
📖
Documentation
https://platform.openai.com/docs/api-reference/chat
📖
Documentation
https://platform.openai.com/docs/guides/embeddings
📖
Documentation
https://platform.openai.com/docs/api-reference/embeddings
📖
Documentation
https://platform.openai.com/docs/api-reference/files
📖
Documentation
https://platform.openai.com/docs/guides/fine-tuning
📖
Documentation
https://platform.openai.com/docs/api-reference/fine-tuning
📖
Documentation
https://platform.openai.com/docs/guides/images
📖
Documentation
https://platform.openai.com/docs/api-reference/images
📖
Documentation
https://platform.openai.com/docs/guides/image-generation
📖
Documentation
https://platform.openai.com/docs/guides/images-vision
📖
Documentation
https://platform.openai.com/docs/models
📖
Documentation
https://platform.openai.com/docs/api-reference/models
📖
Documentation
https://platform.openai.com/docs/assistants/how-it-works/managing-threads-and-messages
📖
Documentation
https://platform.openai.com/docs/api-reference/threads
📖
Documentation
https://platform.openai.com/docs/api-reference/completions

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/openapi/openai-realtime-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-schema/openai-chat-completion-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-schema/openai-embedding-schema.json

Other Resources

🔗
JSONLD
https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/json-ld/openai-context.jsonld

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/openai:openai-realtime-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openai-realtime-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: OpenAI Realtime API
  description: The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.
  version: 2.3.0
  termsOfService: https://openai.com/policies/terms-of-use
  contact:
    name: OpenAI Support
    url: https://help.openai.com/
  license:
    name: MIT
    identifier: MIT
servers:
- url: https://api.openai.com/v1
security:
- ApiKeyAuth: []
tags:


# --- truncated at 32 KB (143 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/openai/refs/heads/main/openapi/openai-realtime-api-openapi.yml