One API for every AI video use case

Send one prompt. Get back a finished, minutes-long video — plus an editable project you can regenerate scene by scene.

The pipeline behind Vivideo, our own AI video app.

RequestPOST /v1/videos
{
  "prompt": "A 60-second cinematic reveal
             of an electric grand tourer",
  "duration_sec": 60,
  "tier": "premium",
  "aspect_ratio": "16:9"
}
01planningScript + shot list
02assetsVoices, characters, places
03producingEvery scene rendered
04editingCut, music, captions
05exportingFinal encode
Delivered videomp4 · 1080p

A 60-second cinematic reveal of an electric grand tourer.

Video models make clips a few seconds long. Finished videos take a pipeline.

Some things models can't make at all — like real footage of Istanbul for a travel video. So every AI video app ends up building the same pipeline on top of the models, then maintaining it for good.

  1. 01Write a script
  2. 02Split it into scenes
  3. 03Pick the best model for each scene
  4. 04Pull in real footage where models can't
  5. 05Stitch it with voiceover and music
  6. 06Check the quality
  7. 07Rebuild parts of it every time a new model ships

Longvid is that pipeline behind one API call.

  • Send a prompt, get back the finished video.
  • Every scene comes back editable — regenerate one at a time.
  • We route each scene to the best model as new ones ship every week.

We built it for Vivideo, our own AI video app, because the third-party API we used before kept failing us.

One call to create, then poll or wait for a webhook

POST a prompt to /v1/videos and the studio runs the whole production. Poll the video until its status is terminal, or register a webhook and stop polling.

01planning

Story, shot list and storyboard.

02assets

Voices, characters and places.

03producing

Every scene is rendered.

04editing

Cut, music and captions.

05qc

Quality check.

06exporting

Final encode.

Ship it, or approve the plan first

By default the video renders straight through. Set approval: manual and it stops at the storyboard so you can approve, decline, or pick a tier before anything is rendered.

Know exactly where it is

The video object carries status, stage and progress.pct. When it's done, you get a signed video_url, thumbnail, duration and scene count.

Typical wall time: a few minutes per minute of video.

A prompt in. A finished video out.

JSON in, JSON out. Send a brief and read the video object back — status, stage, storyboard and the signed URL when it lands.

curl -X POST https://api.longvid.ai/v1/videos \
  -H "Authorization: Bearer lv_live_..." \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: gt-reveal-001" \
  -d '{
    "prompt": "A 60-second cinematic reveal of an electric grand tourer",
    "duration_sec": 60,
    "tier": "premium",
    "aspect_ratio": "16:9"
  }'
  • One endpoint to create, one to poll, one webhook when it is done
  • Same account and credits — no separate plan to enable the API
  • Idempotency keys, per-video webhooks and signed URLs built in

Then poll or wait. Read GET /v1/videos/{id} no more than every 10 seconds, or register a webhook and get video.completed when the file is ready.

Not one opaque file. An editable project.

Every video comes back as a storyboard of scenes, each one you can regenerate on its own. Change a delivered video by telling the director what you want, in words.

Edit a delivered videoPOST /v1/videos/{id}/edits
{
  "instruction": "Re-make scene 3 at dusk
                  and re-voice the closing line."
}

The director does the change and delivers the next version, or quotes the work first so you can approve it. The video's URLs always point at the latest cut.

Scenes are first-class

The storyboard array lists every scene, its plot and its state. Regenerate one scene without touching the rest.

Open it in the studio

Every video has a project_id. app.longvid.ai/studio/{project_id} opens it for new takes and another export — the same project your users can edit.

Model-agnostic on purpose

A new model ships almost every week. We route each scene to the model that wins for that shot, and swap in new ones as they land — so you never rebuild your pipeline again.

Veo 3.1

Video generation

Seedance 2.5

Video generation

Kling

Video generation

ElevenLabs

Voice

Video generation is routed per scene across Veo 3.1, Seedance 2.5 and Kling through fal; voice is ElevenLabs. Where models can't produce a shot, we pull in real footage instead.

The whole pipeline runs on Python on AWS, and LLMs write the script, plan the scenes and orchestrate the run. When a better model appears, we route to it — the API you call stays the same.

Pay for the video you generate

Buy credits, spend them per second of finished video. Three tiers, priced per minute; you pick the tier per video.

budget

$6/ minute

600 credits / minute

The cheapest way to render.

standard

Default
$12/ minute

1,200 credits / minute

The default tier.

premium

$35/ minute

3,500 credits / minute

Highest-fidelity output.

  • 1 credit = $0.01
  • Charged per second of delivered video, rounded up
  • Requested length is prepaid, then settled to the real length
  • Credits are valid 12 months — no subscription, no seats, no minimums

New accounts start with welcome credits. A 45-second standard video is 900 credits ($9.00).

Get an API key

Questions

It turns one prompt into a finished, minutes-long video. It writes the script, splits it into scenes, routes each scene to the best model, pulls in real footage where models fall short, and stitches it with voice, music and captions. You get the video plus an editable project.

Today, AI video apps that would otherwise build and maintain this pipeline themselves. Over time, any developer who needs video from an API.

Yes. Every video comes back as a storyboard of scenes you can regenerate one at a time. You can also edit a delivered video by telling the director what to change in plain words, and open the project in the studio for new takes and another export.

A model API gives you a clip of a few seconds. Longvid is the pipeline above the models: planning, scene splitting, per-scene model routing, real footage, voice, editing, QC, retries, queues, webhooks and billing — so you make one call instead of building and maintaining all of that.

Video generation is routed per scene across Veo 3.1, Seedance 2.5 and Kling through fal; voice is ElevenLabs. We stay model-agnostic on purpose and swap in new models where they win, so the API you call stays the same.

Pay as you go with credits (1 credit = $0.01). Videos are priced per minute at three tiers — budget $6, standard $12, premium $35 — and charged per second of delivered video. Credits are valid 12 months, with no subscription.

It runs Vivideo, our own AI video app, in production. We built it to power a real product before opening it up.

Make your first video

Create a key in Settings, paste it into the curl, and your first video is queued.