←back to thread

OpenAI charges by the minute, so speed up your audio

(george.mand.is)
678 points georgemandis | 1 comments | 25 Jun 25 13:17 UTC | HN request time: 0.001s | source
Show context
tmaly ◴[25 Jun 25 16:43 UTC] No.44379291[source]▶
The whisper model weights are free. You could save even more by just using them locally.
replies(1): >>44380262 #
1. pzo ◴[25 Jun 25 18:13 UTC] No.44380262[source]▶
but this is still great trick if you want to reduce latency or inference speed even with local models e.g. in realtime chatbot