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 / Syntax | What it does | Notes |
|---|---|---|
| aspect_ratio | Aspect ratio | other 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 |
| duration | Video duration | v.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 |
| model | Model version (now supports | v3.5/v4/v4.5/v5/v5.5/v5.6/v6/c1 |
| prompt | Prompt <= 5000 characters | JSON body field of the PixVerse video generation endpoints. |
| quality | Video quality ("360p", "540p", "720p", "1080p") | JSON body field of the PixVerse video generation endpoints. |
| seed | Random seed, | range: 0 - 2147483647 |
| generate_multi_clip_switch | Supported in | v5.5/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 / Syntax | What it does | Notes |
|---|---|---|
| generate_audio_switch | Supported in | v5.5/v5.6/v6/c1 models. Audio switch. Controls whether the video has audio. true: Audio on , false: Audio off . default value : false |
| sound_effect_switch | Supported in | v5 models and below. |
| sound_effect_content | Supported in | v5 models and below. Activated when sound_effect_switch=true, Describe the sound effect you want. Leave blank for auto generation. |
| lip_sync_tts_switch | Supported in | v5 models and below. Set to true if you want to enable this feature. Default is false. |
| lip_sync_tts_content | Supported in | v5 models and below. ~140 (UTF-8) characters |
| lip_sync_tts_speaker_id | Supported in | v5 models and below. id from Get speech tts list |
Image & Template Inputs (3)
| Command / Syntax | What it does | Notes |
|---|---|---|
| img_id | Image ID from Upload image API | single image or single-image templates |
| img_ids | img_ids is only for multi-image templates | ex) "img_ids ":[0,0] |
| template_id | Template ID (template_id must be activated before use) | JSON body field of the PixVerse video generation endpoints. |
Endpoints & Required Headers (4)
| Command / Syntax | What it does | Notes |
|---|---|---|
| POST /openapi/v2/video/text/generate | Create a text-to-video generation task | Requires API-KEY and a unique Ai-trace-id (UUID) header per request. |
| POST /openapi/v2/video/img/generate | Create an image-to-video generation task | Takes img_id from an uploaded image. |
| API-KEY | Required request header carrying your PixVerse platform key | Header, not a body field. |
| Ai-trace-id | Required request header: a UUID unique to each request | Used for tracing; reusing a value across requests is not allowed. |
Model IDs (6)
| Command / Syntax | What it does | Notes |
|---|---|---|
| c1 | Latest PixVerse model generation | Set as the model field value. |
| v6 | Sixth-generation model | Supports the newer aspect ratio set and audio switch. |
| v5.6 | Model version with audio generation support | Set as the model field value. |
| v5.5 | Model version supporting audio and multi-clip switches | Set as the model field value. |
| v4.5 | Earlier model version | Duration options differ from v6/c1. |
| v3.5 | Oldest listed model version | 1080p 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.