One video API
for everything you ship
Subtitles, renders, AI video, images, voice-over and publishing behind one REST API and one key. The same platform your own agent can drive over MCP.
What you can call
Every capability below is a live endpoint, generated from the same registry the reference is built from.
Subtitles & captions
GuideWord-by-word subtitles with Whisper timings, AI emphasis and 116 styles.
Video renders
GuideQueue a render, take the webhook instead of polling, download the mp4.
AI video generation
GuideText to video, faceless scenes and clip extension, straight from your backend.
AI images
GuideGenerate, restyle, crop and cut out backgrounds at scale.
Voice-over & music
ReferenceText to speech on any layer, Whisper alignment and AI songs.
Publishing
ReferenceSchedule a finished video and read the calendar back.
From a URL to a subtitled mp4
Four calls, with the real endpoint names. Nothing here is pseudo-code.
export AUTOSTUD_API_KEY="sk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
export MEDIA_URL="https://cdn.example.com/interview.mp4"
# 1. A project to hang the timeline on.
VIDEO_ID=$(curl -s -X POST https://autostud.ai/api/v1/actions/videos.create \
-H "Authorization: Bearer $AUTOSTUD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"video_name":"Interview clip","video_type_id":"timeline","video_format":"portrait","video_lang":"en"}' \
| jq -r .data.video_id)
# 2. Transcribe and style the subtitles.
curl -X POST https://autostud.ai/api/v1/actions/subtitles.generate \
-H "Authorization: Bearer $AUTOSTUD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"video_id":"'"$VIDEO_ID"'","media_url":"'"$MEDIA_URL"'","style_preset":"beast","words_per_group":3,"enable_emphasis":true}'
# 3. Render it.
curl -X POST https://autostud.ai/api/v1/actions/renders.create \
-H "Authorization: Bearer $AUTOSTUD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"video_id":"'"$VIDEO_ID"'","video_type_id":"timeline","video_format":"portrait"}'
# 4. Stop polling: register the webhook once.
curl -X POST https://autostud.ai/api/v1/webhooks \
-H "Authorization: Bearer $AUTOSTUD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://your-app.com/hooks/autostud","events":["render.completed","render.failed"]}'Or let an agent do it
The same platform, described for machines: one MCP URL, a Markdown version of every page, and errors that say how to recover.
Before you write a client
Do I need a paid plan to try it?
No. Keys are minted in the dashboard, and a sk_test_ key runs the whole request and stops before any write, credit spend or webhook. Live calls spend credits.
How do I get the finished file?
Register a webhook once and every render and generation reports itself, signed and retried. Polling the render or the generation works too, if that suits your stack better.
Is there a rate limit?
Yes, per key, and you never have to guess it: GET /api/v1 returns your key's limits and its usage so far.
Can an AI agent use this without me writing code?
Yes. The MCP page mints a key and hands back a connection URL: paste it into Claude, Cursor or ChatGPT and the same API is available as tools.
Ready to create?
Start generating viral videos in minutes. No credit card required for the free trial.