Feature requests

In the scene timeline, ability to select a group of successive scenes and preview them in order to lower the generating response time and gain time.

Can we have options to pause, slowdown, and give emphasis indications so that the ai voice over can be under contro like human voice reading. Right now the AI sure does follow punctuation marks, but then in some cases to give longer pause we cannot go beyond the grammatical borders of punctuation as the sentence will look out of context and stretched. Can we have an alternative option like a punctuation code through which the AI voiceover can be customised?

When the voiceover pronounces a word, it is highlighted in the subtitles. A setting would allow to choose its color. Thank you!

it will help with making more entertaining and relevant images for videos instead of hoping the B-roll is relevant to script to video. the most popular video generators have this like autoshorts.ai and shortx ai which are my favorite right now.

There are a wide variety of Anglo voices to choose from. But not one African-American voice is available for me to use on my videos.

Be able to clone my voice similar as dine using AI voices so that I do not have to do voiceovers for each video using my voice manually

I hope Pictory can add AI human talking avatar. And e can have personalised face and custom voice.

Hi, just wondering if there is a way to download the story/script before rendering/generating the video. Sometimes I change the script after the scenes are applied and then I don't have an updated copy of the script to do my voiceover unless I go scene by scene. It would be much more efficient to download the script and read from that rather than reading scene by scene. Thanks.

i would like to be able to go back and edit the script after it is generated to make major changes and add more story line in then regenerate. it is awkward to add 1 slide at a time

Our Vietnamese customers would like to create video by feature Script to Video. But in the present, only English is supported. I understand what problem that our customers facing. So I propose my idea to Pictory AI if they could implement Vietnamese language for those features: Script to Video Text to Speech as well (very appreciate) Many thanks if you could help us, Best regards, Viet Anh MKT A Youtuber

Much better subtitles, faster by importing & aligning an existing transcript: The transcription quality is ok. But this means still about 30-50 wrong words in a 10 minute German or English transcript for me. With OpenAI Wisper (medium), I get it down to 4-6 mistakes. The same with Speechmatics. And a lot of us Creators will RECORD/read videos from a script (with some of us getting this almost 100% right), so we already have a perfect transcript with (almost) no errors. It would be awesome if we could import that better transcript (.srt or vtt or whatever with timestamps) and have Pictory do it’s magic to align it to the words (like Descript does it when importing transcripts), so we can do the word level editing (and even more awesome if a “reading script” without timestamps could be re-aligned in a later version). I would gladly use & pay the same amount of credits as needed for a “transcription from scratch” for that. Currently, I would use the Pictory transcription to do the edits and use the other transcript (from Whisper) as a transcript, but it would be so much easier to have it in one: We would spot the last 6 errors while editing the audio, would not have to fix the 30 errors (native transcription), and any word-level edits we do would already be in that corrected and exportable transcript.

Just for an artistic point of view and modify the original vidos

Once selected, there is no way to check what was the original duration of a visual. Sometimes, you need to know this duration in order to adjust your scene. Thank you Pictory, you are the best!

Your audience overall would benefit from being able to have more variety. your company would also benefit because more and more African Americans are starting to use these tool. best to provide the voices for them before your competition decide to cater to them.

We can save a bunch of time text to speech and narrate our own videos. It would make our followers relate to us better and trust us more.