Voice chatting

Models 4

• Gen 3
  GPT Realtime 2

  By OpenAI

  GPT-Realtime-2 is OpenAI’s live voice model with GPT-5-class reasoning, built for voice agents that can listen, reason, use tools, recover from interruptions, and respond naturally in real time. It supports longer 128K context sessions, controllable tone, stronger domain vocabulary, parallel tool calls, and adjustable reasoning effort.

  🎤Voice agents🎤Voice assistants🎙Voice chatting
  NewMultimodal

  Released 1mo ago
• Gen 3
  OpenRouter Text to Speech

  By OpenRouter

  OpenRouter TTS is OpenRouter’s unified text-to-speech interface for accessing multiple speech-generation models through one API layer. It standardizes voice generation across providers, supporting streaming audio output, customizable voices, and multimodal workflows without provider-specific integration complexity.

  🔊Text to speech🎙Voice chatting🎙️Voiceovers
  NewMultimodal

  Released 2mo ago
• Gen 3
  GPT Realtime 1.5

  By OpenAI

  gpt-realtime-1.5 is OpenAI’s flagship real-time voice model for audio-in, audio-out use cases like voice agents and customer support, with support for text, audio, and image inputs and text and audio outputs.

  🎙Voice chatting🔊Text to speech🎤Voice assistants
  Multimodal

  Released 4mo ago
• Gen 3
  FireRedChat

  By FireRedTeam

  FireRedChat is a fully self-hosted system for building real-time, full-duplex voice AI agents.

  🎙Voice chatting🗣️Speech to speech🎤Voice assistants
  Multimodal

  Released 9mo ago