jimeng-api-video-gen

(project - Skill) Generate AI videos using Volcengine Jimeng Video 3.0 Pro API. Use when users request video generation from text prompts or images, including…

INSTALLATION
npx skills add https://github.com/wvlvik/toy-skills --skill jimeng-api-video-gen
Run in your project or agent environment. Adjust flags if your CLI version differs.

SKILL.md

$27

**Generated Video:**

[Download Video](https://github.com/wvlvik/toy-skills/blob/HEAD/skills/jimeng-api-video-gen/VIDEO_URL)

**Generation Info:**

- Prompt: [User's original prompt]

- Duration: [Video length in seconds]

- Mode: [Generation mode used]

- FPS: [Frames per second]

- Save Path: [Local file path, if applicable]

Example Output

**Generated Video:**

[Download Video](https://example.com/video.mp4)

**Generation Info:**

- Prompt: A golden retriever running through a field of sunflowers, warm afternoon sunlight

- Duration: 5 seconds

- Mode: t2v_720p

- FPS: 24

- Save Path: /generated_videos/dog_sunflowers.mp4

API Configuration

ParameterValueDescription
Endpoint\https://visual.volcengineapi.com\API base URL
Submit Action\CVSync2AsyncSubmitTask\Submit async generation task
Query Action\CVSync2AsyncGetResult\Query task result
Version\2022-08-31\API version
Service\cv\Service name for signing
Region\cn-north-1\Region for signing

Generation Modes

Pro Version (1080P HD)

Modereq_keyDescription
ti2v_projimeng_ti2v_v30_proText-to-video + Image-to-video (first frame) Pro

1080P Version

Modereq_keyDescription
t2v_1080pjimeng_t2v_v30_1080pText-to-video 1080P
i2v_first_1080pjimeng_i2v_first_v30_1080Image-to-video (first frame) 1080P
i2v_first_tail_1080pjimeng_i2v_first_tail_v30_1080Image-to-video (first & last frame) 1080P

720P Version

Modereq_keyDescription
t2v_720pjimeng_t2v_v30Text-to-video 720P
i2v_first_720pjimeng_i2v_first_v30Image-to-video (first frame) 720P
i2v_first_tail_720pjimeng_i2v_first_tail_v30Image-to-video (first & last frame) 720P
i2v_recamera_720pjimeng_i2v_recamera_v30Image-to-video (camera movement) 720P

Command-Line Options

\\\

scripts/generate_video.py PROMPT [OPTIONS]

Arguments:

PROMPT Text prompt for video generation (required)

Options:

--mode MODE Generation mode (default: t2v_720p)

Pro: ti2v_pro

1080P: t2v_1080p, i2v_first_1080p, i2v_first_tail_1080p

720P: t2v_720p, i2v_first_720p, i2v_first_tail_720p, i2v_recamera_720p

--duration SECS Video duration: 4, 5, 6, 8, 10 (default: 5)

--fps FPS Frames per second: 24, 25, 30 (default: 24)

--image URL Input image URL for image-to-video (first frame)

--tail-image URL Tail image URL for first & last frame mode

--seed INT Random seed for reproducibility

--output PATH Download video to file

--json Output raw JSON response

Environment Variables:

VOLC_ACCESSKEY Access Key ID (required)

VOLC_SECRETKEY Secret Access Key (required)

JIMENG_VIDEO_API_URL API endpoint (default: https://visual.volcengineapi.com)

JIMENG_VIDEO_API_TIMEOUT Request timeout seconds (default: 300)

JIMENG_VIDEO_POLL_INTERVAL Polling interval seconds (default: 5)

JIMENG_VIDEO_MAX_POLL_ATTEMPTS Max polling attempts (default: 120)

\\\

Video Specifications

Duration Options

DurationUse Case
4sQuick clips, social media
5sDefault, general purpose
6sShort scenes
8sMedium-length content
10sLonger narratives

FPS Options

FPSUse Case
24Cinematic look (default)
25PAL video standard
30Smooth motion, NTSC standard

Authentication

This skill uses Volcengine IAM v4 signature authentication (HMAC-SHA256). The signing process:

  1. Build canonical request with headers: \content-type;host;x-content-sha256;x-date\
  1. Calculate SHA256 hash of canonical request
  1. Derive signing key: secret_key → date → region → service → "request"
  1. Sign the string-to-sign with derived key
  1. Add \Authorization\ header to request

Reference: HTTP请求示例

Error Codes

CodeMessageDescription
10000SuccessRequest successful
50411Pre Img Risk Not PassInput image failed content check
50511Post Video Risk Not PassOutput video failed content check
50412Text Risk Not PassInput text failed content check
50429Request Has Reached API LimitRate limit exceeded, retry later
50500Internal ErrorServer error
timeoutRequest timeoutIncrease JIMENG_VIDEO_API_TIMEOUT

Input/Output Limits

Input Images (for image-to-video):

  • Format: JPEG, PNG only
  • Max size: 15MB per image
  • Max resolution: 4096×4096

Output:

  • Format: MP4
  • URL validity: 24 hours
  • Generation time: 2-10 minutes depending on duration and mode

Reference Documentation

BrowserAct

Let your agent run on any real-world website

Bypass CAPTCHA & anti-bot for free. Start local, scale to cloud.

Explore BrowserAct Skills →

Stop writing automation&scrapers

Install the CLI. Run your first Skill in 30 seconds. Scale when you're ready.

Start free
free · no credit card