OpenAI 推出 GPT-Realtime-2、GPT-Translate 與 GPT-Whisper：全新 SOTA 即時語音 API
Original: [AINews] GPT-Realtime-2, -Translate, and -Whisper: new SOTA realtime voice APIs
OpenAI has continued to expand the reach of its GPT-5 technology, officially launching three new voice and audio APIs: GPT-Realtime-2…
OpenAI 推出全新一代即時語音與音訊 API，包含 GPT-Realtime-2、GPT-Translate 以及 GPT-Whisper。這些 API 將 GPT-5 的強大能力導入語音領域，提供全新業界領先（SOTA）的即時語音互動、多語言翻譯與語音識別效能，展現了 OpenAI 將 GPT-5 架構全面鋪設至各類應用場景的野心。
OpenAI has continued to expand the reach of its GPT-5 technology, officially launching three new voice and audio APIs: GPT-Realtime-2, GPT-Translate, and GPT-Whisper. This marks OpenAI setting a new state-of-the-art (SOTA) benchmark in real-time voice interaction, cross-language translation, and speech recognition (Speech-to-Text).
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Latent Space →Summaries are AI-generated; the original article is authoritative.