Create Render Job
Start a video render job
Start a video render job usingDocumentation Index
Fetch the complete documentation index at: https://docs.viggle.ai/llms.txt
Use this file to discover all available pages before exploring further.
multipart/form-data.
- On-Demand: Upload
ref_imageanddriving_videodirectly — no preprocessing, no stored assets. Costs 1 credit/second of video. - Reusable Assets: Pre-create characters and scenes (both free) for reuse across renders. Each render costs 1 credit/second.
- Fast Mode: Set
fast=truefor 2x rendering speed at 2x credit cost. Requires adriving_videoupload or ascene_id.
Error Handling
If the request fails, the response includes a structured error with anerror_code:
| Code | Cause | Fix |
|---|---|---|
CS-ORAU-001 | Missing API key | Add Authorization: Bearer sk-... header |
CS-ORAU-002 | Invalid API key | Check your key is correct |
CS-ORIV-001 | Missing reference image | Upload ref_image |
CS-ORIV-002 | Missing driving video | Upload driving_video or provide scene_id |
CS-ORIV-004 | Video too long | Keep under 5 minutes |
CS-ORCR-001 | Insufficient credits | Top up credits |
error_code and your job ID.
Examples
On-Demand Render (upload files directly)
Reusable Assets Render (pre-created character + scene)
Next Steps
After creating a render job, poll Get Job Status every 3-5 seconds (no auth required). Whenstatus is complete, use the cdn_url field to download the final video.Authorizations
API key passed as Bearer token
Body
Character reference image file (PNG, JPG). Use this or ref_image_url.
URL to a character image. The server fetches it. Use instead of ref_image file upload.
"https://example.com/character.png"
Driving video file (MP4). Use this or driving_video_url.
URL to a driving video. The server fetches it. Use instead of driving_video file upload.
"https://example.com/dance.mp4"
ID of a ready character (for preprocessed renders)
"char_550e8400e29b41d4"
ID of a ready scene (for preprocessed renders)
"scene_660e8400e29b41d4"
JSON string mapping segment UUIDs to character IDs (for multi-character render)
"{\"person_a1b2c3d4\": \"char_alice\", \"person_e5f6g7h8\": \"char_bob\"}"
Avatar model. V3_Preview uses a different rendering model with a dedicated GPU pool. Scenes preprocessed on one model cannot be rendered on the other.
V4_Preview, V3_Preview Background handling: original (default, person removed via AI inpainting), solid (single color), transparent (alpha mask for compositing)
original, solid, transparent RGB string for solid background color, e.g., "0,255,0". Only used when background_mode is solid.
"0,255,0"
Enable fast mode for 2x rendering speed. Costs 2x credits. Requires a driving_video upload or a scene_id.
Response
Render job created
"job_abc123xyz"
"queued"
The render mode (e.g. full_pipeline, preprocessed, fast)
"full_pipeline"
URL to poll for job status
"/api/render/job_abc123xyz"
URL to get job status
"/api/render/job_abc123xyz"

