Vidu Q3 Text To Video

From 84 credits/sec
ae_vidu_q3_text_to_video

Create a 1–16-second video from a text prompt. Choose the aspect ratio, resolution, duration, and whether to generate sound.

VideoAudio
From 84 credits/sec

Pricing

From 84 credits/sec
ResolutionCharge
360p / 540p84 credits/second
720p / 1080p / Not specified185 credits/second

When duration is omitted, billing is based on five seconds. Starting price applies to Resolution: 360p.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducibility. If None, a random seed is chosen.—
request_body.audiobooleanNoWhether to use direct audio-video generation. When true, outputs video with sound.true
request_body.promptstringYesText prompt for video generation, max 2000 characters—
request_body.durationintegerNoDuration of the video in seconds5
request_body.resolutionenum (360p | 540p | 720p | 1080p)NoOutput video resolution720p
request_body.aspect_ratioenum (16:9 | 9:16 | 4:3 | 3:4 | 1:1)NoThe aspect ratio of the output video16:9

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_vidu_q3_text_to_video' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "9:16",
      "audio": true,
      "duration": 8,
      "prompt": "1950s winter, Guanzhong village, Shaanxi, China. Photorealistic period drama, handheld documentary camera, cold OVERCAST GREY-BEIGE sky, strictly desaturated EARTHY BROWN / dust / clay palette. NO cyan, NO teal, NO green cast, NO blue sky. 9:16 vertical. ONE continuous 8-second shot, no cuts. Camera eases back from medium-close to medium, revealing the bare locust tree, a rammed-earth wall and firewood.\n\nEXACTLY THREE middle-aged peasant women in worn padded cotton jackets and dark headscarves squat close under the tree, All three stay in frame the whole time. No one looks at camera. \n\n0-3s WOMAN A (left, sly, low husky voice) leans in, lowers her voice, pitch RISES on the question then falls to a breathy whisper, speaking Guanzhong-accented Mandarin with earthy rural retroflex sounds, NOT broadcast-standard Mandarin: 「你听见没?兰花家那媳妇——又走了一个。」 Her lips move clearly only while speaking and close when she stops.\n\n3-6s WOMAN B (middle, sharp-tongued, higher nasal voice) CUTS IN before A fully finishes, clicks her tongue, glances toward the lane, pitch lifts, urgent and fast: 「嘘!小声些!嫁一任,克一任,这都第四个了!」 A breath and hesitation, natural overlap.\n\n6-8s WOMAN C (right) says nothing: she raises her eyebrows, gives a warning look, and puts a hand on B'\''s sleeve. A and B freeze mid-gesture. All three turn their eyes together toward the village path. A single footstep on frozen earth. Half a beat of silence.\n\nAUDIO: three DISTINCT female voices with different pitch, pace and accent, emotionally acted dialogue, not narration; a layered ambient bed of wind in bare branches, one far-off chicken, low room tone and a single distant footstep, voices above it. NO music, NO subtitles, NO on-screen text.\nNO face morphing, NO extra people, NO duplicated limbs, NO semi-transparent ghosts, NO modern clothing, NO smiling, NO color cast, NO text, NO watermark.",
      "resolution": "540p"
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "d81033e2-4d9d-484b-baf1-9595b0c49a78"
}