Create audio descriptions of visual content, such as images and videos. Descript, Caption AI, Trint, and IBM Watson Captioningare good tools for generating captions and descriptions for videos. Source: about 1 year ago

You could check on this for transcription. Source: over 1 year ago

There's simple ones like Trint (https://trint.com/) for transcription of interviews and things like Grammarly for improving text. ChatGPT is also good at improving text: chat.openai.com/. Source: over 1 year ago

If not, see how you get on with Trint. It’s AI transcription but you should find it more accurate than Premiere (and you can use it to quickly create SRT files after the transcript has been reviewed/corrected). Trint is very good. Source: over 1 year ago

The client I’m working for currently turned me on to https://trint.com/. It’s a transcription service that syncs the searchable transcript to the time code of the clip. Script has bad timecode for a cut? Search the text to jump to the correct time. Bad inflection on the end of a sound bite? Search for the word with a period after it, so you only get sentence ending instances of the word. It has made my life so... Source: almost 2 years ago

Shotstack - API to generate and edit video at scale. Free up to 20 minutes of rendered video per month. - Source: dev.to / over 1 year ago

That's where solutions like Shotstack can help. Shotstack provides a cloud based video editing API and a robust hosting infrastructure. This allows you to Simultaneously edit and render multiple videos in a powerful cloud infrastructure while not having to worry about Setting up your own servers. You can use SDK for Python, Nodejs, Ruby, or PHP to develop your automation. - Source: dev.to / over 1 year ago

Hi all. I am a founding team member of Shotstack.io. We provide a cloud-based video-editing API infrastructure and we're giving $10,000 credits to eligible startups. Source: almost 2 years ago

Not sure if this is exactly what you’re talking about: https://shotstack.io/. Source: almost 2 years ago

A few things have changed but nothing major. I created a folder inside of /lib for the files being used in edit-video.js. I did this because the amount of steps needed to actually edit the video together justifies being split up. So far, I've been able to attach the audio files from the Google Cloud text-to-speech API to the screen shots from Puppeteer. I haven't been able to find the same amount of time to make... - Source: dev.to / almost 2 years ago