topaz/interpolate/video

Name: Topaz Interpolate Video
Author: Topaz Labs

Interpolate Video is Topaz Labs's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Input

Video Url(string)

URL of the video to retime / interpolate

Target Fps(integer)

16120

Target frames per second for the interpolated output. Range: 16 to 120.

Model(string)

Frame interpolation model. Apollo is general-purpose; Chronos targets real-world motion; Aion handles extreme/complex motion. Allowed values: Apollo, Chronos, Aion.

Slowdown Factor(integer)

Slow-motion factor: 2 makes the output twice as long at the target FPS (2x slow motion), up to 8x. 1 keeps the original speed. The extra generated frames are billed like interpolated frames. Range: 1 to 8.

H264 Output(boolean)

Whether to use H264 codec for output video. Default is H265.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDtopaz/interpolate/video

Input Schema

5 parameters · 0 required · 5 optional

Parameter	Type	Required	Description
`model`	string	Optional	Frame interpolation model. Apollo is general-purpose; Chronos targets real-world motion; Aion handles extreme/complex motion. · Options: Apollo, Chronos, Aion · Default: "Apollo" ApolloChronosAion
`video`	string	Optional	URL of the video to retime / interpolate
`target_fps`	integer	Optional	Target frames per second for the interpolated output. · Min: 16 · Max: 120 · Default: 60
`H264_output`	boolean	Optional	Whether to use H264 codec for output video. Default is H265. · Default: false
`slowdown_factor`	integer	Optional	Slow-motion factor: 2 makes the output twice as long at the target FPS (2x slow motion), up to 8x. 1 keeps the original speed. The extra generated frames are billed like interpolated frames. · Min: 1 · Max: 8 · Default: 1

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "Apollo",
  "video": "https://v3.fal.media/files/kangaroo/y5-1YTGpun17eSeggZMzX_video-1733468228.mp4",
  "target_fps": 60,
  "H264_output": false,
  "slowdown_factor": 1,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Topaz Interpolate Video

API README

Video

Video brings a dedicated workflow to the topaz/interpolate/video workflow for video work in video production. The endpoint is especially useful when a project has a defined transformation goal and needs a repeatable request contract instead of an ad-hoc desktop step. Teams can place this named operation inside review, asset preparation, and publishing pipelines while keeping the original request attached to every result. Interpolate Video is Topaz Labs's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification. Because topaz/interpolate/video is a separate catalog entry, evaluations should use this route’s own inputs, output expectations, and billing behavior. This capability boundary is specific to the endpoint named above.

The mandatory portion is no mandatory fields declared by the schema. For example, the route documentation includes “https://v3.fal.media/files/kangaroo/y5-1YTGpun17eSeggZMzX_video-1733468228.mp4”. Video exposes video, target_fps, model, slowdown_factor, H264_output as its documented request surface. video controls uRL of the video to retime / interpolate; target fps controls target frames per second for the interpolated output; model controls frame interpolation model. Apollo is general-purpose; Chronos targets real-world motion; Aion handles extreme/complex motion; model accepts Apollo, Chronos, Aion; slowdown factor controls slow-motion factor: 2 makes the output twice as long at the target FPS (2x slow motion), up to 8x. 1 keeps the original speed. The extra generated frames are billed like interpolated frames; H264 output controls whether to use H264 codec for output video. Default is H265. Applications can submit that exact shape asynchronously, retain the chosen arguments in job metadata, and collect the resulting media URL for review or publishing.

Highlights

Motion-compensated interpolation. Topaz Interpolate Video creates intermediate frames between source frames to raise playback frame rate or support slow-motion delivery.
Smoother temporal cadence. Added frames reduce visible judder when motion is retimed or converted to a higher-frame-rate presentation.
Source-motion guidance. The existing clip defines subject movement and camera trajectory, keeping the operation focused on temporal reconstruction.
Post-production flexibility. Interpolated output gives editors more options for slow motion, standards conversion, and fluid playback.

Pricing

Billing option	Price
Billing formula	`(usage.duration ?? 10) * (params.model == "Apollo" ? ((((usage.width ?? 1920) * (usage.height ?? 1080)) > 2073600) ? 0.069 : 0.0345) : params.model == "Chronos" ? ((((usage.width ?? 1920) * (usage.height ?? 1080)) > 2073600) ? 0.069 : 0.0345) : ((((usage.width ?? 1920) * (usage.height ?? 1080)) > 2073600) ? 0.196 : 0.0575)) * ((params.target_fps ?? 60) / 60) * (params.slowdown_factor ?? 1)`
Catalog base price	`$0.345000`

When to Use

Scenario	Why it fits
Choose Video	Use it when the job specifically calls for video and the route’s documented input contract matches assets already available in your workflow.
Keep the request reproducible	Use the required inputs explicitly, then record optional choices alongside the prompt for repeatable reruns.
Build controlled creative variations	Change one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions.
Integrate asynchronous delivery	Use this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact.
Validate before a large batch	Run representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production.

Prompt Guide

Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for topaz/interpolate/video.

{
  "model": "Apollo"
}

Technical Specs

Specification	Details
Model ID	`topaz/interpolate/video`
Execution mode	`async`
Task type	`video`
`video`	`string` · optional
`target_fps`	`integer` · optional · min `16` · max `120`
`model`	`string` · optional · choices: `Apollo`, `Chronos`, `Aion`
`slowdown_factor`	`integer` · optional · min `1` · max `8`
`H264_output`	`boolean` · optional