Welcome to Pictory's API Documentation Hub

Empower your teams, users, and leaders with easy-to-use video tools that allow them to create videos in minutes.

Save freelance and agency budgets with our industry-leading AI-powered text-to-video and video summarization API.

Browse millions of videos with our AI-powered search function - less searching more accurate b-roll for your videos

api developers page for pictory


Problem #1: Video creation is time-consuming and expensive

  • An average video project takes at least 5 weeks to complete.
  • High-end video agencies can cost up to $500k/per asset (and for SMBs, freelancers on UpWork run $5k-$10k/per video asset).
  • Businesses are losing speed, money, and time for content assets that are not evergreen nor are built for omnichannel experiences.

Problem #2: Video creation at scale is nearly impossible

  • The new social media era has greatly increased the appetite for video across businesses. The times of low-frequency video creation (1-2 videos per quarter) are long gone.
  • Our users estimate that their companies push out over 10 internal/external videos per week.
    Video is ubiquitous across function areas (HR, product, sales, marketing) and is the single most important form of communication today.
  • The utilization rate of existing video footage is low. Our users estimate their teams are sitting on over 150 hours of video recordings, and repurpose only 1-2 hours for their channels.

Problem #3: Video tools ≠ smart and intuitive

  • After interviewing over 230 B2B professionals, we realized a simple truth - users who are not trained video editors are being asked to create videos for their job. Today, all employees are content creators, not just marketers.
  • Programs like Adobe Premier and Da Vinci have complicated and overwhelming UI.


Empower your marketing, sales, QA, product, consulting, and HR teams to create videos instantly

Pictory offers a cutting-edge AI-powered platform that summarizes videos and transforms text to video, in minutes. Our platform helps businesses around the world create videos quickly and easily, without any video editing required - all through our APIs.

How does it work?

We have built and trained powerful AI models that fit into existing workflows.

Here's how our AI video summarizer works:

  1. First, our platform extracts audio from video inputs (think Teams/Zoom recordings, webinars, or event recordings) and transcribes it into text while removing filler words and pauses automatically.
  2. We use proprietary models built and trained in-house to summarize the transcriptions into "Highlights."
    The "Highlights" can then be easily edited by the user and generated into short-form videos (perfect for Reels and TikTok).

Here is how our famous text-to-video technology works:

  1. First, our platform takes your text inputs (for example, video scripts generated by ChatGPT) and finds themes and keywords.
  2. Users are then able to choose from a variety of modern caption-style templates.
  3. The script input is then matched magically with video footage from royalty-free media libraries like Getty Images and Storyblocks.
  4. Users can add a text-to-speech AI narration or provide their own voice-over for the video.
  5. Finally, your video is generated for you to preview, get feedback from colleagues, and make further edits in our full Story Editor.

API Pricing

Text to Video API is based on usage from a finished video perspective. We create an annual contract that outlines the number of finished video minutes that a client would use on an annual basis and price from there. (Pricing ranges from $.20 per minute to <$.10 per minute).

Video Summarization API is also based on usage but in this model, it is for ingest and egress. Ingest is separated from egress to give you the most favorable rates for video processing. Ingest ranges ($.03 per minute to $.01 per minute) with egress being the same as above (pricing ranges from $.20 per minute to <$.10 per minute).

Growth Numbers

Pictory is growing and acquiring users rapidly.


  • >400% paid user growth since January 2023
  • >15k videos generated on average daily
  • Nearly doubled the team since the end of 2022
    1.2M sign ups


Doesn’t something like this exist today? If not, why?
Kinda of. There are many front-end video editing platforms (InVideo, Vouch, Kapwing), but none that are providing access to their API.

Are you a video editing tool?
Yes and more! We'ree an end-to-end video solution for all parts of your video workflow.

Why now?
“User-generated content (UGC) is not done by professional [Video Editors]. The best user-generated content eventually becomes those people gravitated in the professional world.” Michael Eisner.