Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. OpenAI Realtime API
Developer Tools
OpenAI Realtime API icon

OpenAI Realtime API

by OpenAI

OpenAI's Realtime API lets developers build speech-to-speech voice agents that work directly with audio, keep conversation state and call tools. It is for developers building voice assistants and other low-latency conversational apps.

API·Usage-based

View documentation(opens in a new tab)

About OpenAI Realtime API

Key features of OpenAI Realtime API

  • Speech-to-speech with audio in and audio out
  • Conversation state kept within the session
  • Tool calling, MCP servers and connectors during a conversation
  • Barge-in and natural turn-taking with voice activity detection
  • WebRTC for browsers and WebSocket for servers
  • Ephemeral client secrets for browser and mobile clients
  • Agents SDK support with handoffs and guardrails

Who OpenAI Realtime API is for

  • Developers building voice assistants
  • Customer support teams building phone or web voice agents
  • App developers adding live voice conversation
  • Teams building realtime translation or transcription

How to use OpenAI Realtime API

  1. 1

    Step 1: Create an OpenAI API key in the API dashboard.

  2. 2

    Step 2: On your server, create an ephemeral client secret with POST /v1/realtime/client_secrets.

  3. 3

    Step 3: In your frontend, define a RealtimeAgent with instructions using the Agents SDK (@openai/agents/realtime).

  4. 4

    Step 4: Open a RealtimeSession with a model such as gpt-realtime-2.1 and connect using the ephemeral key.

  5. 5

    Step 5: Attach tools, handoffs and guardrails to the agent, and tune voice activity detection for turn-taking.

OpenAI Realtime API FAQ

How much does the OpenAI Realtime API cost?

It is billed per token, with separate rates for audio and text and for input and output. OpenAI's pricing page lists the current rates for each model.

Does the Realtime API support WebRTC?

Yes. Browser apps typically connect over WebRTC, and server-side apps can connect over WebSocket.

Can the Realtime API call tools?

Yes. Realtime sessions can call functions, MCP servers and connectors while the conversation continues.

How do I migrate from the Realtime API beta?

Remove the OpenAI-Beta: realtime=v1 header, create ephemeral credentials with POST /v1/realtime/client_secrets, use /v1/realtime/calls for WebRTC, and update session and event shapes to the GA format.

Technical details

Environment variables

Details

Pricing
Usage-basedUsage-based, billed per token, with separate rates for audio and text input and output. Cached input is cheaper.
Type
API
Platforms
  • API
Categories
Developer ToolsAIAudio
Added
Oct 1, 2026
OpenAI iconPublisherOpenAI

Built from public sources

We put this page together from OpenAI Realtime API’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with OpenAI Realtime API.

Work at OpenAI Realtime API? Claim the listing to manage it yourself.

Something wrong here?

More from OpenAI

View publisher
ChatGPT Space iconChatGPT SpaceOpenAI · SubscriptionChatGPT Space is a shared place in ChatGPT for pages, files, spreadsheets and slides that you build with ChatGPT and your teammates. It replaces Library and is available on Pro, Business and Enterprise plans.Productivity · SubscriptionChatGPT Work iconChatGPT WorkOpenAI · FreemiumChatGPT Work is an agent in ChatGPT that takes action across your apps and files and turns a goal into finished work such as sheets, slides, docs and web apps. It can stay with a project for hours.Productivity · FreemiumOpenAI Dots iconOpenAI DotsOpenAI · SubscriptionDots are always-on agents in ChatGPT that take on ongoing responsibilities and keep making progress between conversations. You choose which apps they use and when they need your approval.Productivity · Subscription

Related tools

See more
AssemblyAI iconAssemblyAIAssemblyAI · Usage-basedAssemblyAI is a voice AI platform with APIs for speech-to-text, text-to-speech, speech understanding and LLM access. Developers use it to build voice agents, notetakers and call analytics.Developer Tools · Usage-basedResemble AI iconResemble AIResemble AI · Usage-basedResemble AI detects AI-generated audio, video and images and offers watermarking and identity tools. It is used for fraud prevention, meeting security and content moderation, through an API or built-in integrations.Developer Tools · Usage-basedGladia iconGladiaGladia · Usage-basedGladia is an audio infrastructure API that transcribes speech in real time or from uploaded files and adds audio intelligence such as sentiment and entity detection. It is aimed at developers building voice products.Developer Tools · Usage-based