- OpenAI has released three new voice models—GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper—that integrate advanced reasoning capabilities matching GPT-5 into real-time conversations. These models can now translate across 70+ languages and transcribe live speech.
- The introduction of these voice models signifies a significant advancement in AI technology, enabling more sophisticated interactions between humans and machines in real time.
- These innovations further blur the line between human-like communication and machine intelligence, offering new possibilities for applications such as language translation and transcription services.
Originally published at the-decoder.com. Curated by AI Maestro.
Stay ahead of AI. Get the most important stories delivered to your inbox — no spam, no noise.