Minimax H3 Singularity Reference To Video API Documentation

Minimax H3 Singularity Reference To Video API Documentation

Playground

MiniMax H3 Singularity Open Weights Reference to Video generates coherent 480P / 540P / 768P videos from prompts and multimodal references, guided by up to 9 reference images, 3 reference videos, and 3 reference audios, with native stereo audio and flexible reference-based video generation on WaveSpeedAI infrastructure. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Run the open-weights edition of MiniMax H3 Singularity on WaveSpeedAI’s own GPU infrastructure. This endpoint is separate from the official minimax/h3 API: same model family, independently hosted, with its own 480p/540p/768p/1080p resolutions and per-second pricing.

MiniMax H3 Singularity is an omni-modal video model that generates picture and native stereo audio in a single pass. In reference-to-video mode you guide the generation with up to 9 reference images, 3 reference videos, and 3 reference audio tracks, then tell the model — in the prompt — what each reference is for.

How to Use References

Refer to every input in the prompt with an angle-bracket tag: <Picture 1>, <Video 1>, <Audio 1>, and so on. The tags must be written exactly like that, with the brackets — plain text such as Picture 1 is treated as ordinary words, not a reference.

Assign a job to each reference. Explicit assignments work far better than leaving the model to guess:

> “Use the character from <Picture 1>, place them in the setting from <Picture 2>, and match the camera motion of <Video 1>.”

Numbering

• Tags are numbered per type, in the order the inputs are provided: images are <Picture 1>…<Picture 9>, standalone audios are <Audio 1>…, videos are <Video 1>…<Video 3>.
• A reference video’s own soundtrack is used automatically and occupies the earliest <Audio …> slots; any standalone reference_audios you provide are numbered after the video soundtracks. If you only need the video’s audio, refer to it via its <Video …> tag.

Rules

• At least one reference image or video is required. Audio cannot be provided alone.
• reference_videos works at any output resolution. References are always conformed to a 480p pixel budget internally (they carry identity and motion, not output detail), so a 768p render with references stays practical.
• Reference video soundtracks are picked up automatically; total reference-video duration shares a 15-second budget and longer inputs are trimmed fairly.

How to Write a Great Prompt

Write the prompt as a timeline with a schedule, and weave the reference tags into it:

1. Style & references — establish the look and say which reference drives identity, style, motion, or voice.
2. Timeline — timestamped beats: “[0s-3s] <Picture 1> stands on the balcony from <Picture 2> … [3s-6s] turns toward camera and smiles …”.
3. Camera — explicit movement, including when to hold: “slow orbit, no cuts”.
4. Audio — an Audio: line with entrance cues; reference an input voice or track by tag if you want it matched.
5. On-screen text — spell out readable words in quotes and add “no subtitles, do not add other text.”

Parameters

At least one of reference_images, reference_videos, or reference_audios is required.

Specifications

Pricing

Output video is billed per generated second, plus per-reference charges:

Example: a 10s 480p video with 2 reference images and a 5s reference video costs 10 × $0.05 + 2 × $0.02 + 5 × $0.05 = $0.79.

Model

Powered by the community MiniMax H3 Singularity v1.3 checkpoint. Supports the same reference input format as WaveSpeed MiniMax H3.

Related Models

• Singularity Reference-to-Video
• Singularity Reference-to-Video LoRA

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "16:9",
  "resolution": "480p",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-singularity/reference-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters