Build more natural voice experiences with GPT‑Live‑1 in the API

Introducing gpt-realtime and Realtime API updates

We’re releasing a more advanced speech-to-speech model and new API capabilities including MCP server support, image input, and SIP phone calling support.

How we built a realtime system for responsive voice AI in six months

GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.

Introducing GPT-Live

A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.

Customizable, no-code voice agent automation with GPT-4o

Retell AI is transforming the call center with AI voice automation powered by GPT-4o and GPT-4. 1.

How Tolan builds voice-first AI with GPT-5.1

Tolan built a voice-first AI companion with GPT-5. 1, combining low-latency responses, real-time context reconstruction, and memory-driven personalities for natural conversations.

Introducing the Realtime API

Developers can now build fast speech-to-speech experiences into their applications

GPT-5.3 Instant: Smoother, more useful everyday conversations

GPT-5.1: A smarter, more conversational ChatGPT

We’re upgrading the GPT-5 series with warmer, more capable models and new ways to customize ChatGPT’s tone and style. GPT-5.

Advancing voice intelligence with new models in the API

Explore new realtime voice models in the OpenAI API that can reason, translate, and transcribe speech, enabling more natural and intelligent voice experiences.

GPT-5.5 Instant: smarter, clearer, and more personalized

GPT-5. 5 Instant updates ChatGPT’s default model with smarter, more accurate answers, reduced hallucinations, and improved personalization controls.

Introducing ChatGPT and Whisper APIs

A frontend-backend architecture for tool calls in full-duplex speech models

The paper introduces a frontend‑backend architecture for full‑duplex speech‑to‑speech models that enables tool calls while preserving natural conversational flow. The frontend emits a delegation token and streams ASR transcripts to a text‑based backend LLM, which performs tool calls and returns results that are re‑injected into the frontend via a lightweight prefill‑and‑repeat mechanism before streaming TTS synthesis. In single‑turn evaluations the system achieves 92‑97% tool‑call recall, 81.2% accuracy in rejecting irrelevant calls, and competitive performance on Full‑Duplex‑Bench‑V3 and EVA‑Bench when paired with a large backend model.