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.
From 84 credits/sec
Pricing
From 84 credits/sec
| Resolution | Charge |
|---|---|
| 360p / 540p | 84 credits/second |
| 720p / 1080p / Not specified | 185 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.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.seed | integer | unknown | No | Random seed for reproducibility. If None, a random seed is chosen. | — |
request_body.audio | boolean | No | Whether to use direct audio-video generation. When true, outputs video with sound. | true |
request_body.prompt | string | Yes | Text prompt for video generation, max 2000 characters | — |
request_body.duration | integer | No | Duration of the video in seconds | 5 |
request_body.resolution | enum (360p | 540p | 720p | 1080p) | No | Output video resolution | 720p |
request_body.aspect_ratio | enum (16:9 | 9:16 | 4:3 | 3:4 | 1:1) | No | The aspect ratio of the output video | 16:9 |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeySubmit 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
{
"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"
}




