grok-imagine-video
Non-official Grok video generation with text-to-video, image-to-video, multiple reference images, 1–15 second duration, and 720P output.
InputPrompttext
Models1available
FlowAsyncresult URL
Price2 quotanon-official channel
Examples
Prompt to video, in context
Text-to-video · no reference images
Prompt
She touches her cheek and smiles gently, then smiles wide looking into the camera, camera not moving, text and items stay exactly the same not moving.
Text-to-video · no reference images
Prompt
The monkey slowly turns a page, focused, reading. A small baby monkey dressed in a baby suit comes to distract him. No talking.
Text-to-video · no reference images
Prompt
Drone footage, flying at the front of the building.
Capabilities
What you can build with grok-imagine-video
Prompt driven generation
Submit a concise prompt and get production-ready video output through one TTAPI job.
Core controls only
Keep integration simple with prompt, model, output settings, and callback handling.
Async result flow
Use polling or webhook callbacks so long-running generations do not block your UI.
Ready for product UI
Return grok-imagine-video results that can be displayed, stored, or passed into downstream workflows.
Pricing
Per-action, in quota
Usage is metered in quota by model, action, and output settings.
API request
grok-imagine-video operations and request fields
Use the endpoint below with your TTAPI key and the request fields shown.
/grok/generationsSubmit a non-official Grok video task with video_length, resolution_name, reference images, and an optional callback.
Official reference/grok/fetchRetrieve a non-official Grok video result.
Official reference/grok/extensionsExtend a non-official Grok video.
Official referenceHeaders
TT-API-KEYstringrequiredYour TTAPI API key.
Content-TypestringrequiredUse application/json.
Body
promptstringrequiredGeneration prompt. Base and 1.5 accept up to 4,096 characters; 1.5 Fast supports longer prompts.
modelenumoptionalDefaults to grok-imagine-video-1.5-fast. Also supports grok-imagine-video and grok-imagine-video-1.5.
aspect_ratioenumoptionalDefaults to 16:9. Supported: 2:3, 3:2, 1:1, 9:16, and 16:9.
video_lengthstringoptionalDefaults to 10. Fast supports 6–30 seconds; base and 1.5 support 1–15 seconds. Base supports up to 15 seconds with one image and up to 10 with multiple images.
resolution_nameenumoptionalDefaults to 720p. 480p and 720p work across all models; 1080p is supported only by grok-imagine-video-1.5.
refer_imagesstring[]conditionalReference-image URLs. Fast accepts up to 7; base accepts multiple; 1.5 requires exactly one image.
voice_idenumoptionalVoice role ID for the generated video audio. Options include carina, zagan, helix, orion, luna, iris, altair, and zenith.
hook_urlstringoptionalCallback URL notified when the job completes or fails; otherwise retrieve the result through Fetch.
Integrate
From key to first result
Copy the resolved endpoint, authentication headers, and request body for this model.
curl --request POST \
--url https://api.ttapi.io/grok/generations \
--header 'TT-API-KEY: $TTAPI_KEY' \
--header 'Content-Type: application/json' \
--data '{"model":"grok-imagine-video","prompt":"a joyful panda rides a roller coaster through a green park","aspect_ratio":"2:3","video_length":"6","resolution_name":"720p","voice_id":"luna"}'