1
malusama Oct 18, 2024 这玩意估计就是模型支持语音的输入输出。。毕竟早就是多模态的了
|
2
kyor0 Oct 18, 2024
4o 是多模台的
|
3
cyp0633 Oct 19, 2024
如果是 whisper ,效果会远不如讯飞
|
4
FlashEcho Oct 19, 2024
官方文档里就有: https://platform.openai.com/docs/guides/speech-to-text
The Audio API provides two speech to text endpoints, transcriptions and translations, based on our state-of-the-art open source large-v2 Whisper model. |