tech
May 7, 2026
OpenAI launches new voice intelligence features in its API
The new features could be handy for customer service systems, but OpenAI says they have applications that work across a variety of other fields, including education and creator platforms.
TL;DR
- OpenAI's API now includes GPT‑Realtime‑2 for realistic vocal simulations and complex requests.
- GPT‑Realtime‑Translate offers real-time translation for over 70 input and 13 output languages.
- GPT-Realtime-Whisper provides live speech-to-text capabilities.
- These features are intended for a wide range of applications, including customer service, education, media, events, and creator platforms.
- OpenAI has implemented guardrails to prevent misuse for spam, fraud, or online abuse, with conversation halts for guideline violations.
- Translate and Whisper are billed per minute, while GPT-Realtime-2 is billed by token consumption.