@tankots@WisprFlow love wispr flow - I use it for everything - including screen sharing into tailscale controlled mac minis - the pasting doesn't work there tho - so built a helper: https://t.co/iEFrzm2ElI
I would love if wispr flow just did this natively and didn't need a hacky solution tho!
If you're a researcher looking to:
→ conduct rigorous studies on how multiple models can outperform the frontier
→ leverage data from the largest LLM marketplace (150+ trillion tokens processed per month)
... DM me with your work!
We have an exciting role coming in the future, but might fill it opportunistically.
@WisprFlow is great until you try using it through screen share.
I got tired of manually fixing it, so I built a tiny helper that intercepts the paste attempt and injects the transcript into the screen share properly.
https://t.co/iEFrzm2ElI
@mvanhorn great article, some things to add
- DJI Mic Mini > Gooseneck mic for most situations
^you can use it on the go - it has no latency unlike other bluetooth mics
- @aquavoice has a better / less annoying mobile app than wispr
Today, we’re excited to introduce Miso One, the most emotive voice model in the world.
Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.
We’ve open-sourced the model weights, with API access coming soon.
Hear how Miso One sounds in the thread below.
Today, we’re excited to introduce Miso One, the most emotive voice model in the world.
Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.
We’ve open-sourced the model weights, with API access coming soon.
Hear how Miso One sounds in the thread below.