Realtime API

Model-level realtime API for text and audio input/output over WebRTC, WebSocket, or SIP, with function calling.

2 provider sources
Realtime API vendor website preview
Vendor website ↗
Provider typeNative realtime multimodal model API
Best fitProduct and engineering teams building a spoken application around a realtime model instead of a packaged contact-center product.
Team sizesstartup; mid-market; enterprise; developer
Call surfacesWebRTC; WebSocket; SIP; API / SDK
Pricing modelToken-based API pricing for text, audio, and image modalities; audio input/output rates are published per million tokens.
Pricing signalGPT-Realtime audio $32 per million input audio tokens and $64 per million output audio tokens.
Free plan or trialNot publicly documented

Realtime API pricing and budget

GPT-Realtime audio $32 per million input audio tokens and $64 per million output audio tokens.

Token-based API pricing for text, audio, and image modalities; audio input/output rates are published per million tokens.

Not publicly documented

Catalog pricing checked September 4, 2026. Confirm current terms in the provider sources.

Compare the complete workload cost →

Key capabilities

  • audio-to-audio conversation
  • WebRTC
  • WebSocket
  • SIP
  • tools

Runtime and fit

Voice stack
Native audio input/output with tool calling
Telephony
SIP connection; carrier integration remains buyer responsibility
Call controls
Not publicly documented
Integrations
Not publicly documented
Knowledge and data
Not publicly documented
Languages
Not publicly documented

What stands out

GPT-Realtime accepts and returns audio directly, while the Agents SDK supplies transport helpers plus tools, guardrails, handoffs, and session history.

Considerations

Not a turnkey contact center. Implement telephony operations, identity, tools, monitoring, evaluation, retention, and escalation.

Before you decide

Questions about Realtime API

How should I budget for Realtime API?

The published pricing signal is: GPT-Realtime audio $32 per million input audio tokens and $64 per million output audio tokens. The recorded pricing model is: Token-based API pricing for text, audio, and image modalities; audio input/output rates are published per million tokens. Ask the provider for a current quote covering the same workload, channels, subscriptions, usage and implementation costs.

Can Realtime API use my existing data?

The listed knowledge and data sources include Not publicly documented. Confirm permissions, freshness and failure behavior for your exact systems with the provider.

What should I test in a Realtime API pilot?

Run representative calls with the same instructions and escalation rules. Record voice quality, completed tasks, handoffs and total cost. Check these cautions: Not a turnkey contact center. Implement telephony operations, identity, tools, monitoring, evaluation, retention, and escalation.

Evaluate language support in real calls

Test recognition, speech quality, interruptions, language switching, tool use, and human transfer with your own calls in the required language. Availability can vary by model, plan, and phone route.

DocsBot documents multilingual voice workflows and Japanese support. Verify the exact voice, phone path, and transfer behavior in your pilot. Review DocsBot language information ↗

Other providers’ language claims reflect cited vendor material; confirm Japanese and other required languages directly with each provider.

Listing does not imply endorsement or a performance guarantee. This directory is published by DocsBot. Editorial policy

Your business. Your shortlist.

Is Realtime API right for you?

Start with your website. Answer a few focused questions, then get a personalized PDF with fit, trade-offs, alternatives and a pilot plan for your call flow.

Privacy policy ↗

AI voice agent directory

Your personalized recommendation

Provider research → short interview → your PDF.