Pruna P Video 2 Pro Serverless API
Native-audio AI video from text or first/last-frame images.
POST /v2/p-video-2-pro · 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 blacksmith in a dim workshop forge hammers a glowing orange blade on an iron anvil, bright sparks bursting on each strike, then lifts the blade and plunges it into a water barrel. Sound: the rhythmic clang of hammer on steel, the low roar of the forge, and a sharp hiss of steam as the steel is quenched.",
11 "resolution": "768p",
12 "mode": "speed",
13 "duration": 6,
14 "aspect_ratio": "16:9",
15 "prompt_upsampler": "turbo",
16 "seed": 42,
17}
18job = client.submit_async("p-video-2-pro", **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("p-video-2-pro", **payload) 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 blacksmith in a dim workshop forge hammers a glowing orange blade on an iron anvil, bright sparks bursting on each strike, then lifts the blade and plunges it into a water barrel. Sound: the rhythmic clang of hammer on steel, the low roar of the forge, and a sharp hiss of steam as the steel is quenched.",
11 "resolution": "768p",
12 "mode": "speed",
13 "duration": 6,
14 "aspect_ratio": "16:9",
15 "prompt_upsampler": "turbo",
16 "seed": 42,
17}
18job = client.submit_async("p-video-2-pro", **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("p-video-2-pro", **payload)API Endpoint
https://api.segmind.com/v1/p-video-2-proParameters
promptrequiredstringDescribe the scene, action and camera movement. P Video 2 Pro generates audio along with the video, so ambience and sound effects can be prompted too.
aspect_ratiooptionalstringOutput frame shape. Ignored when a reference image is supplied, since the image sets the frame.
"16:9""16:9""9:16""4:3""3:4""3:2""2:3""1:1"durationoptionalintegerTarget length of the generated video. The model treats this as a target and may return a slightly shorter or longer clip; billing follows the video you receive.
5Range: 5 - 15imageoptionalstring (uri)Optional first-frame image to animate. Supplying one switches the model to image-to-video and sets the frame, so the aspect ratio is taken from the image.
last_frame_imageoptionalstring (uri)Optional reference image for the final frame, to steer where the shot ends up.
modeoptionalstringWhich recipe the model uses. Speed is faster and cheaper per second; quality spends more compute on the same prompt and is billed at a higher rate.
"speed""speed""quality"prompt_upsampleroptionalstringHow much the model expands a short prompt before generating. Independent of the generation mode.
"turbo""off""turbo""max"resolutionoptionalstringOutput resolution. 768p costs more per second of video than 480p.
"768p""480p""768p"seedoptionalintegerFixed seed for reproducible output. Use -1 for a new random result each run.
-1Range: -1 - 2147483647Response 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
POST /v2/p-video-2-proSubmit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- 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.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out