PixVerse Commands & Prompt Reference

26 commands & parameters · 5 categories · Source: PixVerse Platform API Docs

PixVerse's video API is a flat JSON body with one wrinkle worth knowing before you start: nearly every capability is gated by model version. Duration ranges, aspect ratios, audio generation, multi-clip output, and lip sync each have their own supported model list, so the model field is not just a quality dial - it decides which other parameters are even legal in the same request. This page lists every documented field from the official OpenAPI reference alongside those version constraints.

Two headers are mandatory and easy to miss: API-KEY carries your platform key, and Ai-trace-id must be a UUID that is unique per request rather than per session. On the body side, prompt accepts up to 5000 characters, seed spans the full 32-bit range for reproducible runs, and the image-to-video endpoint swaps in img_id (or img_ids) from an uploaded asset.

All Commands

Generation Parameters (7)

Command / SyntaxWhat it doesNotes
aspect_ratioAspect ratioother models : 16:9, 4:3, 1:1, 3:4, 9:16 v6/c1 models : 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9
durationVideo durationv.3.5/v4/v4.5 : 5/8 (v3.5 1080p cannot use 8) v5 : 5/8 v5.5/v5.6 : 5/8/10 (1080p cannot use 10) v6/c1 : 1~15
modelModel version (now supportsv3.5/v4/v4.5/v5/v5.5/v5.6/v6/c1
promptPrompt <= 5000 charactersJSON body field of the PixVerse video generation endpoints.
qualityVideo quality ("360p", "540p", "720p", "1080p")JSON body field of the PixVerse video generation endpoints.
seedRandom seed,range: 0 - 2147483647
generate_multi_clip_switchSupported inv5.5/v6 models. Single or multi-clip switch. controls single-clip and multi-clip generation modes. true: Multi-clip , false: Single-clip. default value : false

Audio & Lip Sync Parameters (6)

Command / SyntaxWhat it doesNotes
generate_audio_switchSupported inv5.5/v5.6/v6/c1 models. Audio switch. Controls whether the video has audio. true: Audio on , false: Audio off . default value : false
sound_effect_switchSupported inv5 models and below.
sound_effect_contentSupported inv5 models and below. Activated when sound_effect_switch=true, Describe the sound effect you want. Leave blank for auto generation.
lip_sync_tts_switchSupported inv5 models and below. Set to true if you want to enable this feature. Default is false.
lip_sync_tts_contentSupported inv5 models and below. ~140 (UTF-8) characters
lip_sync_tts_speaker_idSupported inv5 models and below. id from Get speech tts list

Image & Template Inputs (3)

Command / SyntaxWhat it doesNotes
img_idImage ID from Upload image APIsingle image or single-image templates
img_idsimg_ids is only for multi-image templatesex) "img_ids ":[0,0]
template_idTemplate ID (template_id must be activated before use)JSON body field of the PixVerse video generation endpoints.

Endpoints & Required Headers (4)

Command / SyntaxWhat it doesNotes
POST /openapi/v2/video/text/generateCreate a text-to-video generation taskRequires API-KEY and a unique Ai-trace-id (UUID) header per request.
POST /openapi/v2/video/img/generateCreate an image-to-video generation taskTakes img_id from an uploaded image.
API-KEYRequired request header carrying your PixVerse platform keyHeader, not a body field.
Ai-trace-idRequired request header: a UUID unique to each requestUsed for tracing; reusing a value across requests is not allowed.

Model IDs (6)

Command / SyntaxWhat it doesNotes
c1Latest PixVerse model generationSet as the model field value.
v6Sixth-generation modelSupports the newer aspect ratio set and audio switch.
v5.6Model version with audio generation supportSet as the model field value.
v5.5Model version supporting audio and multi-clip switchesSet as the model field value.
v4.5Earlier model versionDuration options differ from v6/c1.
v3.5Oldest listed model version1080p output cannot use the 8 second duration.

Frequently Asked Questions

Why is a parameter being ignored in my PixVerse request?

Most parameters are model-gated. Audio and multi-clip switches are supported on the newer models, while sound effects and lip sync fields apply to v5 and below. Check the model version against the parameter before debugging further.

What duration and quality can I ask for?

It depends on the model: older versions accept 5 or 8 seconds, v5.5 and v5.6 add 10 (not at 1080p), and v6/c1 accept 1 to 15. Quality options are 360p, 540p, 720p, and 1080p.

What headers does the API require?

API-KEY with your platform key, and Ai-trace-id containing a UUID that must be unique for each request.

Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.

Related prompt references

Kling AI (24) · Vidu (24) · MiniMax (Hailuo) (24) · All AI prompt references