HappyHorse 1.0 Serverless API

Cinematic 1080p text-to-video with native audio and lip-sync.

PlaygroundHistory
API
Pricing
~149.07s
POST /v2/happyhorse · 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    "prompt": "A majestic white horse galloping through golden wheat fields at sunset, cinematic slow motion, warm golden hour lighting, dust particles catching sunlight, shallow depth of field, professional nature documentary style",
11    "negative_prompt": "blurry, low quality, distorted, watermark, text",
12    "resolution": "720P",
13    "duration": 5,
14    "aspect_ratio": "16:9",
15    "prompt_extend": True,
16    "watermark": False,
17}
18job = client.submit_async("happyhorse", **payload)
19print(job.request_id)                         # available immediately
20try:
21    result = job.wait(timeout=900, interval=2.0)
22    print(result["status"])                  # COMPLETED
23    print(result.get("output"))              # model output (e.g. video URL)
24except InferenceTimeout as e:
25    print("still running:", e.request_id)    # re-poll later with this id
26except InferenceFailed as e:
27    print("failed:", e.detail)
28
29# Fast models (<=600s) can use the one-liner instead:
30# result = segmind.run("happyhorse", **payload)

API Endpoint

POSThttps://api.segmind.com/v1/happyhorse

Parameters

promptrequired
string

Describe scene, subjects, motion, camera, and audio cues. Cinematic prompts with lighting and camera details produce the best results.

Default: "A majestic white horse galloping through golden wheat fields at sunset, cinematic slow motion, warm golden hour lighting, dust particles catching sunlight, shallow depth of field, professional nature documentary style"
aspect_ratiooptional
string

Aspect ratio for text-to-video only (ignored with image input). 16:9 for landscape, 9:16 for vertical.

Default: "16:9"
Allowed values :
"16:9""9:16""1:1""4:3""3:4"
audio_urloptional
string (uri)

Audio URL (MP3/WAV, 3-30s, max 15MB) for lip-sync. Use speech audio for talking-head or voiceover-driven scenes.

Default: null
durationoptional
integer

Video length in seconds (3-15). 5s is the sweet spot for quality and speed.

Default: 5
imageoptional
string (uri)

First frame for image-to-video mode (URL or base64). Leave empty for text-to-video generation.

Default: null
last_frameoptional
string (uri)

Ending frame for image-to-video mode only. Creates smooth transitions between start and end frames.

Default: null
negative_promptoptional
string

Elements to suppress (blur, artifacts, watermark). Tested: 'blurry, low quality, distorted, watermark, text' works well.

Default: "blurry, low quality, distorted, watermark, text"
prompt_extendoptional
boolean

LLM-rewrites short prompts for cinematic detail. Recommended on for brief prompts, off for precise control.

Default: true
reference_imagesoptional
string[]

Up to 5 reference image URLs (or uploads). Used as character/scene anchors for reference-to-video mode.

reference_videosoptional
string[]

Up to 3 reference video URLs (or uploads). Used as motion/style anchors for reference-to-video mode.

reference_voiceoptional
string (uri)

Audio file URL for character voice cloning in reference-to-video mode.

Default: null
resolutionoptional
string

Output resolution. 720P for fast previews ($0.875), 1080P for final delivery ($1.50).

Default: "720P"
Allowed values :
"720P""1080P"
seedoptional
integer

Reproducibility seed (0-2147483647). Set a fixed seed to reproduce the same output across runs.

Default: null
videooptional
string (uri)

URL of an existing video to edit. Provide this with a prompt to restyle, recolour, or modify the video. Triggers video-edit mode.

Default: null
watermarkoptional
boolean

Adds 'AI Generated' watermark to output. Disable for clean production-ready video.

Default: false

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/happyhorse

    Submit — returns request_id, status_url, response_url

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

    Poll — until COMPLETED or FAILED

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

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (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