Post

Typing is for suckers. Voice ftw. What are you using for dictating? I've been going back an forth between superwhisper and the built in MacOS one Also testing a few others like Tuna

Sam Goff

@samgoff.bsky.social

11 May

Building my own

Wes Bos

@wesbos.com

The transcribing speed seems to be all over the place even with the same models. I wonder if some of them are transcribing it as it's streamed in versus waiting for the audio to finish.

11/5/26, 8:54 pm0 reposts2 likes

Sam Goff

@samgoff.bsky.social

11 May

Yeah, or they’re batching/chunking frames, if I had to guess. I’m designing mine to work locally with the lowest latency I’ve ever measured.

Wes Bos

@wesbos.com

11 May

let me know how it goes! I'm also curious about streaming from hosted models since I'd only use cents a day. the new xai Speech to text model is very accurate and cheap