buzz VS StoryToolkitAI

Easiest 1-click way to install and use Stable Diffusion on your computer."

https://github.com/easydiffusion/easydiffusion

And while Whisper is OpenAI, it is trivial to use locally and extremely usefull

https://github.com/chidiwilliams/buzz

Install this for Resolve

Just use this one: https://github.com/chidiwilliams/buzz

What utilities related to Whisper do you wish existed? What have you had to build yourself?

On the end user application side, I wish there was something that let me pick a podcast of my choosing, get it fully transcribed, and get an embeddings search plus answer q&a on top of that podcast or set of chosen podcasts. I've seen ones for specific podcasts, but I'd like one where I can choose the podcast. (Probably won't build it)

Also on the end user side, I wish there was an Otter alternative (still paid $30/mo, but unlimited minutes per month) that had longer transcription limits. (Started building this, not much interest from users though)

Things I've seen on the dev tool side:

Gladia (API call version of Whisper)

Whisper.cpp

Whisper webservice (https://github.com/ahmetoner/whisper-asr-webservice) - via this thread

Live microphone demo (not real time, it still does it in chunks) https://github.com/mallorbc/whisper_mic

Streamlit UI https://github.com/hayabhay/whisper-ui

Whisper playground https://github.com/saharmor/whisper-playground

Real time whisper https://github.com/shirayu/whispering

Whisper as a service https://github.com/schibsted/WAAS

Improved timestamps and speaker identification https://github.com/m-bain/whisperX

MacWhisper https://goodsnooze.gumroad.com/l/macwhisper

Crossplatform desktop Whisper that supports semi-realtime https://github.com/chidiwilliams/buzz

There's StoryToolkitAI, it's free (But requires Davinci Resolve Studio). It can transcribe and generate subtitles quite accurately. It also has a feature to translate subtitles to English. I haven't tried the translate feature yet, but I've been using this tool for my work a lot. It also supports more languages than resolve's built in transcription and auto subtitle tool.

StoryToolkit AI

I've been using StoryToolkitAI.

If you've got the paid version of Resolve Studio, there's a plugin that's pretty effective for adding captions/generating subtitle files. Story Toolkit AI

I don't know how the situation is with Premiere or MC, I'm sure there are some tools either built-in or third-party, but for Davinci I know for certain of two options — the latest public beta which implements this feature natively (only for English at the moment) or a tool called StoryToolkitAI, which supports a number of languages and has pretty good recognition.

I'm using this for transcription and subtitles. It's very rough right now, but the transcriptions are so good, and right now it's free.

For open or closed captions, or for subtitles traditionally used for accessibility and localization, use a transcription service like rev or Simon Says (or upload to YouTube and download the captions). If you have the Studio version and certain hardware, StoryToolkitAI may be an option.

What you’re looking for is StoryToolkitAI: https://github.com/octimot/StoryToolkitAI/releases