# auray-ai/minimax-h3-v2/text-to-video

`POST https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video` submits; the response carries a `request_id` and the three URLs to use next.

This model cannot be waited on: its jobs outlive any connection worth holding. `POST https://auray.run/auray-ai/minimax-h3-v2/text-to-video` answers `400 model_not_synchronous` and `?wait=` is refused `wait_unsupported`, both before anything is charged. Submit it to the queue and poll `status_url`, stream the status, or pass `?webhook=` to be called when it is done.

One of the models behind Auray's apps.

Price: One price per clip for each length rung — up to 5, 10 and 15 seconds — one list for a clip from words alone and one for a clip with references, each rung's credits in force served by GET /v1/plans as `price_keys` (`video.h3v2.text.<rung>` and `video.h3v2.refs.<rung>`) and quoted when you submit. Refunded if the render fails.

Fields read from https://api.auray.ai/v1/openapi.json on 2026-08-31.

Every error code is explained at https://auray.ai/docs/api/errors.

Address: auray-ai/minimax-h3-v2/text-to-video
Servers: https://queue.auray.run
Scope:   video:write
Auth:    Authorization: Bearer auray_sk_…
API enabled: yes

## What it can do

- `t2v` — Text → Video
- `video-refs` — References: up to 9 pictures (optional); 1 clip (optional); up to 3 sounds (optional)

Length: 4 to 15 seconds
Aspect ratios: 16:9, 9:16
Resolutions: 768p, 480p
Prompt: up to 7,000 characters
Sound: makes its own sound
Priced by: `rung` (the whole rule is under Price)

## Input

- prompt (string, required) — What to film. Name references as <Picture 1>, <Video 1> and <Audio 1>, each kind counted from one in its list's order; the structured form in the guide works best, and plain sentences work too. With no reference, up to 3,800 characters and 4,096 tokens of the model's own tokenizer: prose in English, Indonesian, Chinese, Japanese, Thai or Hindi fits in the 3,800 characters, while rare characters and some scripts take several tokens a character and can reach 4,096 tokens first. Past either, the request is refused with prompt_too_long before anything is charged; a refusal in tokens carries `tokens` and `max_tokens`. Documented range: up to 7,000 characters.
- duration_seconds (integer, optional, default: 5) — Whole seconds; outside 4–15 it is refused with 422 duration_out_of_range, before any charge. Documented range: 4 to 15.
- aspect_ratio (string, optional, default: "16:9", one of: "16:9", "9:16") — 16:9 or 9:16.
- resolution (string, optional, default: "768p", one of: "768p", "480p") — 480p needs at least one picture or clip; from words alone a clip is made at 768p.
- image_references (array of url, optional) — Up to 9 pictures that hold a subject — a face, a costume, a place — named in order as <Picture 1>, the next as the next number. JPEG, PNG or WebP. Accepts image/jpeg, image/png, image/webp. At most 25 MB. Documented range: up to 9. When the request also sends `audio_references`, this model makes the person in a picture here speak or move: a picture you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send `acceptance: {"real_people": "2026-11-03"}` with the request, or accept in the Auray app — and is refused `403 acceptance_required` until then, before anything is charged. A picture made here — a job's result — asks nothing. While uploads are paused here, a picture you upload, or a link from anywhere else, is refused `403 likeness_not_made_here` instead, before anything is charged. The files the examples here send are ours, and are taken.
- video_references (array of url, optional) — One clip whose look and motion the new clip follows, named <Video 1>: H.264 in MP4 or MOV, up to 5.2 seconds. Its own sound is kept: a voice or a sound in it may guide the new clip. Accepts video/mp4, video/quicktime. At most 25 MB. Documented range: up to 1. This model may keep the sound of a clip here as a voice: a clip you upload with a sound track, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send `acceptance: {"real_people": "2026-11-03"}` with the request, or accept in the Auray app — and is refused `403 acceptance_required` until then, before anything is charged. A clip you upload with no sound track asks nothing, nor does one made here. When the request also sends `audio_references`, this model makes the person in a clip here speak or move: a clip you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send `acceptance: {"real_people": "2026-11-03"}` with the request, or accept in the Auray app — and is refused `403 acceptance_required` until then, before anything is charged. A clip made here — a job's result — asks nothing. While uploads are paused here, a clip you upload with a sound track, or a link from anywhere else, is refused `403 voice_sample_not_made_here` instead, before anything is charged. While uploads are paused here, a clip you upload, or a link from anywhere else, is refused `403 likeness_not_made_here` instead, before anything is charged. The files the examples here send are ours, and are taken.
- audio_references (array of url, optional) — Up to 3 sounds — a voice or an ambience — named <Audio 1> and on: WAV, MP3, FLAC or M4A, up to 15 seconds each. A sound needs a picture or a clip beside it, and the 12 files of every kind together are the most one request sends. Accepts audio/wav, audio/x-wav, audio/wave, audio/mpeg, audio/flac, audio/x-flac, audio/mp4, audio/x-m4a. At most 25 MB. Documented range: up to 3. This model may keep the voice in a recording here: a recording you upload, or a link from anywhere else, is taken once your account has accepted, one time, that you have the right to the faces and voices you use — send `acceptance: {"real_people": "2026-11-03"}` with the request, or accept in the Auray app — and is refused `403 acceptance_required` until then, before anything is charged. Or send the request without it. While uploads are paused here, a recording you upload, or a link from anywhere else, is refused `403 voice_sample_not_made_here` instead, before anything is charged; send the request without it. The files the examples here send are ours, and are taken.
- seed (integer, optional) — The same seed with the same prompt and settings makes the same scene again; small details can differ between runs. Outside the range it is refused with 422 seed_out_of_range, before any charge. Documented range: 0 to 4,294,967,295.
- idempotency_key (string, optional) — Your own name for this request. Send the same one twice and the second call is answered with the first request rather than charged again. `Idempotency-Key:` as a header is accepted as an alias — that is the spelling a retrying proxy replays, and the one to use when running a model on `auray.run`, where a request that outlives its connection is answered 504 and recovered by replay. Omit it and the platform mints one.
- acceptance.real_people (string, optional, one of: "2026-11-03") — The version of the words you accept: that you have the right to every face and voice you upload, and to any voice or style you pick that sounds like a real person — it is yours, or you have permission — and that you are responsible for what you make with them.

## Rules

Across fields, as the model's documentation states them; judged before any charge, and warned (Deprecation) until enforcement starts.

- When `audio_references` is sent, send at least one of `image_references` or `video_references`.
- When `resolution` is "480p", send at least one of `image_references` or `video_references`.

## Response

A submit answers the status document (`status`: IN_QUEUE, IN_PROGRESS or COMPLETED; `request_id`;
`queue_position` while queued; `logs`; `metrics`) and then, beside it:
- product (string) — Which of this platform's products ran it.
- provider_job_id (string) — The id the job runs under, once it has been handed to its model — possibly while still `queued`; null before. Quote it to support.
- model (string) — The address that ran it, echoed back.
- engine (string) — The service's own name for the model that ran, where it reports one — a catalogue model's is its `id` on GET /v1/models; null otherwise. What `model` carried before it carried the address.
- attribution (string) — The credit line the model's licence requires you to show; null where none is required.
- credits_charged (integer) — What this job cost. 0 on a replay, or when a pass or a promotion paid for it (`coverage` says which).
- credits_quoted (integer) — What this job costs, in credits: the price it was quoted at submit. Equal to `credits_charged` once it has been charged; while it waits in the queue to start, `credits_charged` is 0 and this is what it will be charged when it starts (a cancel before then costs nothing) — and a replay of a job still waiting quotes the body that job was queued with, which is the one it runs, not the replay's. For a catalogue model it is the hold, and the settle may give part of it back — a settled read's `credits_charged` says what it finally cost.
- coverage (object) — Present when a pass or a promotion paid for this job — `{"by": "pass", "pass": "seedance-2-5"}` or `{"by": "promotion"}`, and `credits_charged` is 0 — or when you hold a pass for this model that did not cover this job: `{"by": null, "miss": {"pass": "video", "why": "door"}}`, `why` being `door` (the pass does not work here) or `shape` (it does not cover this kind of job). Absent otherwise. Send `X-Auray-Covered-Only: 1` to run a job only if a pass or a promotion pays for it.
- credits_remaining (integer) — The balance after it.
- expected_seconds (integer) — A rough render time, for a progress bar; 0 where nothing is published.
- give_up_after_seconds (integer) — The longest this job may take from its submit: the longest it may wait to start (your X-Auray-Request-Timeout, or the product's queue deadline) plus the longest it may run before it is stopped and refunded. Waiting longer is waiting for nothing; the official clients wait this long by default. For a catalogue model the part it may run is its reap: `lifecycle.stall_ceiling_seconds` on GET /v1/models, lengthened for a video asked for more seconds than the length that figure is set for, in proportion to the seconds asked — so this figure, not the listing's, is the one to wait by. Otherwise these are the published limits: we may lengthen them during an incident, never shorten them.
- replayed (boolean) — `true` when your `idempotency_key` matched a job this platform already had. Nothing was charged and nothing was rendered twice.
- waited (boolean) — Present when `wait` was asked for. The rest of this group comes with it.
- timed_out (boolean) — The wait ran out before the job settled. Still a 2xx, never a 408 or 504 — a library that retries on those would resubmit and you would pay twice. Poll `status_url`.
- wait_declined (string) — No seat was free to hold the connection with, so the request was answered at once. `platform_busy`: no product would have helped. `product_busy`: another product's queue might. `account_busy`: you are already waiting on every seat your plan's lanes allow. The job is running either way; poll it.
- status_url (string) — Poll this.
- response_url (string) — Fetch the result from this once the status is COMPLETED.
- cancel_url (string) — `PUT` to this to ask for a cancellation.
Poll `status_url`, fetch `response_url` once COMPLETED, `PUT` `cancel_url` to stop it.

## Price

Price: One price per clip for each length rung — up to 5, 10 and 15 seconds — one list for a clip from words alone and one for a clip with references, each rung's credits in force served by GET /v1/plans as `price_keys` (`video.h3v2.text.<rung>` and `video.h3v2.refs.<rung>`) and quoted when you submit. Refunded if the render fails.

## Paths

POST https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video
  Run auray-ai/minimax-h3-v2/text-to-video
GET https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video/requests/{request_id}
  The result
GET https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video/requests/{request_id}/status
  The status
PUT https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video/requests/{request_id}/cancel
  Ask for a cancellation

## Example

```bash
curl -X POST https://queue.auray.run/auray-ai/minimax-h3-v2/text-to-video \
  -H 'Authorization: Bearer auray_sk_…' \
  -H 'Content-Type: application/json' \
  -d '{"prompt":"a brass orrery on a walnut desk, morning light from a window to the left"}'
```

## Full contract

https://api.auray.ai/v1/models/auray-ai/minimax-h3-v2/text-to-video/openapi.json