there are numerous options that run locally and work just fine for dictation https://superwhisper.com https://handy.computer https://carelesswhisper.com
Turbopuffer team really cooking!
Would be cool to get a wasm build that runs fully on browser
Are you having lawyers getting of MS Word. Ive tried in the past with no success. But this is really cool. Its definitely a problem they have.
Any reason to not use flutter flow with all the AI stuff?
Very different from all the magic mirror sort of solutions. Nice!
Is this opensource or just open eco system?
Damn how is the docker image only 4Mb. Even with the docker slim images they typically are atleast double digit. Nice!
WER scores?
I think people who realize its not about avoiding inconvenience but a tool that will make life significantly easier will kost likely pay. Just like paying for a smartphone or data or broadband.
I've looked at the codebase. The ones I listed do a significant amount of audio processing to get better transcripts, avoid the "Thank you" issues with whisper large turbo, handle bluetooth and noisy environments.…
Are these running whisper underneath?
there are numerous options that run locally and work just fine for dictation https://superwhisper.com https://handy.computer https://carelesswhisper.com
Turbopuffer team really cooking!
Would be cool to get a wasm build that runs fully on browser
Are you having lawyers getting of MS Word. Ive tried in the past with no success. But this is really cool. Its definitely a problem they have.
Any reason to not use flutter flow with all the AI stuff?
Very different from all the magic mirror sort of solutions. Nice!
Is this opensource or just open eco system?
Damn how is the docker image only 4Mb. Even with the docker slim images they typically are atleast double digit. Nice!
WER scores?
I think people who realize its not about avoiding inconvenience but a tool that will make life significantly easier will kost likely pay. Just like paying for a smartphone or data or broadband.
I've looked at the codebase. The ones I listed do a significant amount of audio processing to get better transcripts, avoid the "Thank you" issues with whisper large turbo, handle bluetooth and noisy environments.…
Are these running whisper underneath?