|
1
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
|
|
kyor0Oct 18, 2024
2
4o 是多模台的
|
|
cyp0633Oct 19, 2024
3
如果是 whisper ,效果会远不如讯飞
|
|
FlashEchoOct 19, 2024
4
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. |