Feature requests

Upload audio, have it translate to text and make video from it like text to video feature.

If you could make your platform use AI video that it generates according to script or give people the option to use AI-generated content alongside stock I know that it will make your platform the leading text-to-video generator in the world as no one combines these elements and it is a nuisance to pay multiple subscriptions to get these features most people would prefer it all in one place Canva tried it but their video generator is bad and who would not want to just push a button and boom there is a video generated for you complete with AI scenes most people struggle with prompting so this would help people a lot

This is again a common ask from most of our customers.

Folders are perfect way to Organize everything Uploaded(Images,video,background musics & own voice overs) to Pictory. And a Search Button also required to find the required files in the future use. This way everybody can keep their files clean category wise in separate folders without scrolling a lot. 👉 Ability to move images/video/bgm etc to any folders

Can we have a video clip speed option to either slow down (slow motion) a clip or increase the speed? Not for the entire video, but individual scenes.

I can’t directly make a 3-minute finished video for you, but I can design a full HD video concept + script + scene breakdown so you (or a video editor) can create it with real footage or AI-generated clips. Here’s the plan for your “single man travel & party” video (3 minutes): Title: Waves, Peaks & Beats Duration: 3:00 minutes Mood: Adventurous, romantic, and high-energy party vibe. Music: Starts with a light travel melody → transitions into a party beat. Scene-by-Scene Breakdown 0:00 – 0:20 – Opening: The Journey Begins Slow-motion shots of the man walking along a sunrise beach.Drone shot over the ocean waves.Text overlay: “The World Awaits”Light guitar or soft beats in the background. 0:20 – 0:50 – Mountains & Roads Scenic shots of the man driving on a winding mountain road.Hiking at the mountain peak, arms open wide to the sky.GoPro shot from his perspective looking down a valley. 0:50 – 1:20 – Sea Beach Fun Running into the ocean waves.Throwing water in the air, laughing.Camera pans to beautiful sunset over the sea. 1:20 – 1:50 – Singing & Street Scenes Sitting by a roadside café, singing a romantic travel song.Locals smiling, dancing in small groups. 1:50 – 2:50 – Party Club Night Neon lights, high-energy music kicks in.The man dancing with a group of girls.Slow-motion shots of girls laughing, hands in the air.Drinks clinking, crowd moving to the beat. 2:50 – 3:00 – Closing Shot Walking away from the party towards the night city skyline.Text overlay: “Life is a Journey — Live It”

Create a dynamic video for SD-TV, a web television dedicated to sustainable development. Use inspiring images of local communities, sustainable agriculture, craftsmanship, and ecological innovations. The tone should be engaging, with subtitles in both French and local languages. Scenes to include: Introduction: Images of local communities, agricultural fields, artisans, and women in action. Nature, agroecology, and resource management. Mission of SD-TV: Text: "SD-TV's mission: making scientific, local, and reproducible solutions accessible." Videos of researchers and ecological solutions. SD-TV Objectives: Objective 1: "Make science and local knowledge applicable." (Practical examples of sustainable agriculture.) Objective 2: "Strengthen resilience against environmental challenges." (Local initiatives for climate change.) Objective 3: "Amplify the voice of communities in global SDG debates." Areas of Action: Agriculture, green economy, local entrepreneurship, and citizen engagement. Conclusion: "SD-TV, inspiring change." Text: "Join us for a sustainable future." Subtitles: Include subtitles in French

I would like to propose a feature that allows users to upload a custom JSON file containing both the scene text and an associated visual search prompt for each frame. While your new tool is impressively fast and efficient, the current visual matching system often fails to select contextually appropriate visuals. As a result, users are still required to do extensive manual editing — particularly for true crime and documentary-style videos where visual accuracy is critical. By enabling a structured input format (e.g., JSON), users could define both the narrative and the intended visual prompt per scene. This would allow your AI to more accurately select matching visuals and significantly reduce manual workload, while still leveraging your powerful automation features. This small addition could drastically improve visual relevance and user satisfaction — especially for creators working with high-volume or fact-based content.

“A esposa no mercado: ‘Vamos só pegar o que precisa.’ 15 minutos depois… Carrinho cheio, cartão estourado, e eu segurando a sacola com R$ 300 em alface!”

To add more variety to the automated machine voice-overs in your videos

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

Create nice videos with variety of animation styles for the Text which appears on the video

Publish your videos into multiple languages and get better visibility and user engagement

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