OpusClip - Clips From Video Serverless API

Turn long videos into captioned vertical shorts.

~328.82s
POST /v2/opus-clips-from-video · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
 4
 5# Async (v2) — recommended for long-running / video models.
 6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
 7# deadline and keeps the request_id so you can re-poll later.
 8client = SegmindClient()                      # reads SEGMIND_API_KEY
 9payload = {
10    "video_url": "https://segmind-resources.s3.amazonaws.com/input/opus-clips-from-video-input.mp4",
11    "clip_type": "talking-heads",
12    "custom_prompt": "",
13    "clip_duration_min": 15,
14    "clip_duration_max": 60,
15    "genre": "Auto",
16    "topic_keywords": [],
17    "aspect_ratio": "portrait",
18    "remove_filler_words": False,
19    "skip_curate": False,
20    "video_title": "",
21}
22job = client.submit_async("opus-clips-from-video", **payload)
23print(job.request_id)                         # available immediately
24try:
25    result = job.wait(timeout=900, interval=2.0)
26    print(result["status"])                  # COMPLETED
27    print(result.get("output"))              # model output (e.g. video URL)
28except InferenceTimeout as e:
29    print("still running:", e.request_id)    # re-poll later with this id
30except InferenceFailed as e:
31    print("failed:", e.detail)
32
33# Fast models (<=600s) can use the one-liner instead:
34# result = segmind.run("opus-clips-from-video", **payload)

API Endpoint

POSThttps://api.segmind.com/v1/opus-clips-from-video

Parameters

video_urlrequired
string (uri)

Public long-form video URL, up to 90 minutes. Supports YouTube, Vimeo, Zoom, MP4.

aspect_ratiooptional
string

Output framing. Use portrait for TikTok, Reels, Shorts; landscape for YouTube; square for feeds.

Default: "portrait"
Allowed values :
Portrait"portrait"
Landscape"landscape"
Square"square"
brand_template_idoptional
string

Optional OpusClip style preset for captions and layout. Choose a template to brand clips.

Allowed values (22 total):
Karaoke"preset-fancy-Karaoke"
Gameplay"preset-fancy-Gameplay"
Beasty"preset-fancy-Beasty"
Deep Diver"preset-fancy-Deep_Diver"
Youshaei"preset-fancy-Youshaei"
Pod P"preset-fancy-Pod_P"
Mozi"preset-fancy-Mozi"
Popline"preset-fancy-Popline"
Simple"preset-fancy-Simple"
Think Media"preset-fancy-Think_Media"
+12 more
clip_duration_maxoptional
integer

Maximum clip length in seconds (5-300). Keep 60 or below for shorts.

Default: 60Range: 5 - 300
clip_duration_minoptional
integer

Minimum clip length in seconds (5-300). Set 15-30 for Shorts and Reels.

Default: 15Range: 5 - 300
clip_typeoptional
string

Curation mode. Use talking-heads for podcasts and interviews; generic for prompt-driven clipping.

Default: "talking-heads"
Allowed values :
Talking Heads"talking-heads"
Generic"generic"
custom_promptoptional
string

Describes what to extract; required when clip_type is generic. Example: compile funniest moments.

Default: ""
genreoptional
string

Content genre guiding curation. Use Auto to detect, or set Podcast, Interview, Educational.

Default: "Auto"
Allowed values :
"Auto""Podcast""Interview""Educational""Comedy""Vlog"
remove_filler_wordsoptional
boolean

Removes ums and uhs from clips. Enable for tighter, more polished talking-head cuts.

Default: false
skip_curateoptional
boolean

Skips highlight selection and reframes and captions the whole video. Enable to bypass curation.

Default: false
source_languageoptional
string

Spoken language as an ISO code like en. Leave blank to auto-detect.

topic_keywordsoptional
string[]

Keywords to prioritize during talking-heads curation. Add topics you want clips focused on.

video_titleoptional
string

Optional title giving context to improve curation. Add your video title for relevance.

Default: ""

Response Type

Returns: Video

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/opus-clips-from-video

    Submitreturns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Polluntil COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out