1
malusama 2024-10-18 19:16:01 +08:00 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 2024-10-18 19:43:13 +08:00
4o 是多模台的
|
3
cyp0633 2024-10-19 08:56:56 +08:00
如果是 whisper ,效果会远不如讯飞
|
4
FlashEcho 2024-10-19 19:18:22 +08:00
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. |