Create highlights out of your podcasts, convert them into branded-videos using stock visuals and/or your own images
10
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?
15
Multiple Voices - Add ability for conversations, or multiple contributors to storytelling. Think about a series of sides, some being told by a central character, others contributing. Even a slide where multiple voices are speaking the same message together...perhaps building into a crescendo... Slide 1 - One voice Slide 2 - Two voices Slide 3 - Four voices Slide 4 - A crowd!
10
Can have great niche based images and graphic elements so if you can add those that would be great. We don't have to edit video on another software. Also there not a lot of pictures in pictory. So please add images library from canva.
6
You were onto something when you realized how Elevenlabs models work. I figured this out from day one, every time you render a sentence it's spoken differently. Every project I've had to re-render a few scenes to get the flow to sound correct. Give us a button to "Print the entire audio in one render". This should be an explicit act by the user, not implicitly something it does, and the user should be notified how much of their audio rendering budget will be wiped. It seems this should also be the default for the first render as it achieves the best results. Then revert back to the previous mode where if we change a scene we can re-render it piece-wise. Check the Eleven labs UI where they give you two options: generate and download, as the workflow is generate-listen-reject-generate-listen-reject-generate-listen-approve-download. Best of both worlds. π‘
2
I was looking at a video today and realized it was malformed. It has odd edges and shortened clips. This started as a portrait project, and then became a landscape project. The result here is what happens when Pan and Zoom isn't turned off for everything before the video is generated. Turning that off for all things made the video render properly. I'm trying to find that storyboard link again so I can record this. If you have it, please share it. Since doing these steps resolves the issue, it's not a bug, but it would be a nice improvement to ask the user and make the change if they OK.
0
We need to have a permanent subscription, i only use this because i still have the 50 hours per month and its a good transcriptor, but i really need a lifetime deal, if not i may only pay it once more and im done, its very expensive for a yearly payment, specially due to the limited usefullness
1
upload an audio file (ie podcast) and edit via the transcription
2
Videos, video snippets, GIFs as output to fill your social calendars!
4
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.
8
The AI can't pronounce certain words correctly. But if you spell it with the correct pronunciation, it shows it on the screen. Have two boxes, one for pronunciation and another for what gets shown on the screen.
11
Try the following: Apply a voice-over to the intro scene. Apply a voice-over to the outro scene. Apply a voice-over to the entire video and select βNo, it does notβ at the prompt. Now you have three different voice-overs but you cannot generate the video now (it stops with two error messages) because the feature of three different voice-overs is not supported. Why I want that feature: I want to avoid packing all three voice-overs into one voice-over because I must pay my text-to-speech vendor by seconds. So I wanted to generate the intro and outro only once and just make the rest from scratch.
2
Build https://www.moovly.com/ or others like it within Pictory
0
Similar to typewriter, I'd love to see the ability to have the word that is being spoken highlighted as it's being read.
1
Lots of videos these days are in vertical format - YT shorts, Tiktok etc. Ability to search images & video clips based on aspect ratio would make things much easier.
2