Gemini Omni 1.1 Serverless API
Text-to-video with synchronized native audio, up to 4K.
POST /v2/gemini-omni-1.1 · 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": "Cinematic slow-motion close-up of powerful ocean waves crashing against dark volcanic rocks at golden sunset, white sea spray bursting into the air, the deep thunderous crash of each wave and distant seagull calls perfectly synchronized with the motion, warm rim light, photorealistic, highly detailed, shallow depth of field.",
11 "duration": 5,
12 "resolution": "720p",
13 "aspect_ratio": "16:9",
14}
15job = client.submit_async("gemini-omni-1.1", **payload)
16print(job.request_id) # available immediately
17try:
18 result = job.wait(timeout=900, interval=2.0)
19 print(result["status"]) # COMPLETED
20 print(result.get("output")) # model output (e.g. video URL)
21except InferenceTimeout as e:
22 print("still running:", e.request_id) # re-poll later with this id
23except InferenceFailed as e:
24 print("failed:", e.detail)
25
26# Fast models (<=600s) can use the one-liner instead:
27# result = segmind.run("gemini-omni-1.1", **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": "Cinematic slow-motion close-up of powerful ocean waves crashing against dark volcanic rocks at golden sunset, white sea spray bursting into the air, the deep thunderous crash of each wave and distant seagull calls perfectly synchronized with the motion, warm rim light, photorealistic, highly detailed, shallow depth of field.",
11 "duration": 5,
12 "resolution": "720p",
13 "aspect_ratio": "16:9",
14}
15job = client.submit_async("gemini-omni-1.1", **payload)
16print(job.request_id) # available immediately
17try:
18 result = job.wait(timeout=900, interval=2.0)
19 print(result["status"]) # COMPLETED
20 print(result.get("output")) # model output (e.g. video URL)
21except InferenceTimeout as e:
22 print("still running:", e.request_id) # re-poll later with this id
23except InferenceFailed as e:
24 print("failed:", e.detail)
25
26# Fast models (<=600s) can use the one-liner instead:
27# result = segmind.run("gemini-omni-1.1", **payload)API Endpoint
https://api.segmind.com/v1/gemini-omni-1.1Parameters
promptrequiredstringDescribe the scene, subjects, camera moves and sound design. Supports bracketed timecodes like [0-3s] ... [3-6s], and <IMAGE_REF_0>, <IMAGE_REF_1>, ... to bind reference images.
"Cinematic drone shot gliding through misty pine mountains at sunrise, god rays breaking through the fog, birdsong and gentle wind in the audio, photorealistic, highly detailed."aspect_ratiooptionalstring16:9 landscape or 9:16 vertical.
"16:9""16:9""9:16"durationoptionalintegerVideo length in seconds (3-10). Billed per second of output video.
5Range: 3 - 10first_frameoptionalstring (uri)The video starts exactly from this image.
last_frameoptionalstring (uri)Optional ending frame. With First Frame set, the model interpolates smoothly between the two.
reference_imagesoptionalstring[]1-10 reference images. Subjects/styles are extracted and embedded into a new scene (not used as literal frames). Bind them in the prompt with <IMAGE_REF_0>, <IMAGE_REF_1>, ... Cannot be combined with First/Last Frame.
resolutionoptionalstringOutput resolution. 360p is a draft tier (~1/3 the price, ~2x faster); 1080p costs 1.5x and 4k 3x the 720p rate per second.
"720p""360p""720p""1080p""4k"seedoptionalintegerSeed for reproducible generation. -1 for random.
-1Range: -1 - 999999999999999Response 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/gemini-omni-1.1Submit — 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