Skip to main content
Glama

PixVerse MCP Server by useapi.net (third-party)

Server Details

PixVerse video, images, music and speech: effects, keyframes, lip-sync, extend, music videos

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 38 tools

Disambiguation4/5

The tools are largely distinct by modality and action, and descriptions explicitly cross-reference close alternatives such as create_video vs create_video_frames vs create_transition vs create_video_fusion. A few creation tools overlap conceptually (single-frame, two-frame, multi-frame, reference-based video), which leaves some room for misselection but descriptions provide clear guidance.

Naming Consistency4/5

Almost all tools follow a predictable pixverse_<verb>_<noun> snake_case pattern, with clear prefixes for create/get/list/delete/upscale. Minor deviations like pixverse_motion_control and pixverse_lipsync_video break the strict verb_noun pattern but remain readable and consistent with the overall convention.

Tool Count2/5

With 38 tools, the surface is heavy for any single MCP server, even one covering video, image, music, speech, music video, accounts, files, and jobs. Many actions are necessarily separate, but the count is well above the practical 3-15 range and increases selection burden.

Completeness4/5

Coverage is broad: creation, retrieval, listing, deletion for main media types, plus uploads, account inspection, features, and running-job management. Minor gaps remain, such as no delete operation for speech or music tracks and no delete for uploaded files, but these are workaroundable.

Publisher details

Operator
useapi.net
Operator website
https://useapi.net
Vendor relationship
Independent
Privacy policy
Not provided
Restrictions
Paid useapi.net subscription ($15/month flat). Requires your own PixVerse account. · Publisher source

Available Tools

38 tools
pixverse_cancel_jobStop tracking a running jobA
DestructiveIdempotent
Inspect

Stop tracking a running video, image, music or speech job (from pixverse_list_running_jobs) and free its slot on the account. It does not stop the job at PixVerse. 404 when the id is not running. Cannot be undone. DELETE /scheduler/{id}.

Inputs: id (required).

pixverse_create_final_videoRender a Seedance 2.5 draft in full qualityAInspect

Render a finished seedance-2.5-draft video again with Seedance 2.5 at 1080p or 2160p (4K), on the draft's account, while the draft is valid (its seedance_draft.can_create_final and expires_at in pixverse_get_video; drafts are kept 14 days). Only drafts; other videos: pixverse_upscale_video. Uses PixVerse credits by second and quality (see the pricing page). Waits up to ~50 s, then returns the new video_id for pixverse_get_video. POST /videos/create-final.

Inputs: video_id (required), wait, maxJobs, quality, +1 more.

pixverse_create_imageGenerate imagesAInspect

Generate 1-4 images with Qwen Image (the default), Nano Banana, Seedream, GPT Image or Kling image models, from a prompt and up to 16 reference images (by model). Each model has its own qualities, ratios and reference count (pixverse_get_features lists the image models the plan allows). Uses PixVerse credits per image, free in Relax Mode where the plan includes the model. Waits up to ~50 s and returns each image's image_id and image_url, the first as an image; else the ids for pixverse_get_image. POST /images/create.

Inputs: prompt (required), seed, wait, email, +8 more.

pixverse_create_musicGenerate musicAInspect

Generate a song or an instrumental from a prompt with music-2.6 (MiniMax Music 2.6), music-v1 (ElevenLabs Music), lyria-3-pro-preview (Google Lyria 3 Pro); default music-2.6. Your own lyrics on music-2.6 and music-v1 (else the model writes them), instrumental: true for no vocals, and up to 10 reference images on lyria-3-pro-preview. Uses PixVerse credits per track (see the pricing page). Waits up to ~50 s, then returns the audio_id for pixverse_get_music. POST /music/create.

Inputs: prompt (required), wait, email, model, +4 more.

pixverse_create_music_videoMake a music videoAInspect

Make a full music video from a song (audio_path: an uploaded MP3, 10 seconds to 6 minutes, or a library song) and optionally a character photo: performance (default), expressive or storytelling mode, a style, lyric captions, 720p or 1080p. Credits per second of song by mode and quality; the first music video of every account is free; quote: true answers the exact price and creates nothing. Waits up to ~50 s, then returns the video_id for pixverse_get_music_video. POST /music-video/create.

Inputs: audio_path (required), mode, wait, email, +12 more.

pixverse_create_speechGenerate speechAInspect

Text-to-speech with speech-2.8-hd (10,000 characters), speech-2.8-turbo (10,000 characters), eleven-multilingual-v2 (10,000 characters), eleven-v3 (5,000 characters), eleven-turbo-v2.5 (40,000 characters); default speech-2.8-hd. voice_id comes from pixverse_list_speech_voices; voice settings: speed, volume, pitch, emotion on the MiniMax speech models; speed, stability, similarity_boost on ElevenLabs, plus style and use_speaker_boost on eleven-multilingual-v2 only (other settings are refused). Uses PixVerse credits by characters (see pixverse_list_speech_models). Waits up to ~50 s, then returns the audio_id for pixverse_get_speech. POST /speech/create.

Inputs: text (required), voice_id (required), wait, email, +11 more.

pixverse_create_transitionMulti-frame transition videoAInspect

Generate one video through 2-7 keyframes in order, each move with its own prompt and duration, with v5, v5.5, v5.6 (3 or more frames: v5 only). For two frames on newer or third-party models use pixverse_create_video_frames. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/create-transition.

Inputs: frames (required), seed, wait, audio, +6 more.

pixverse_create_videoGenerate a videoAInspect

Generate a video from text, an image (first_frame_path) or an effect template (template_id from pixverse_list_effects) with PixVerse V6 (default), C1, V5.x or third-party models (Seedance 2.5 / 2.0, Kling 4.0 / O3 / 3.0, Veo 3.1, MiniMax H3, Wan 3.0, Grok Imagine, HappyHorse, FLUX 3, Gemini Omni Flash). Durations, qualities and ratios depend on the model (see the model capabilities page); third-party models need a Pro plan or higher. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/create.

Inputs: seed, wait, audio, email, +18 more.

pixverse_create_video_framesVideo from a first and last frameAInspect

Generate a video that moves from a first frame to a last frame (two uploaded images), with V5.6 (default), V5.5, V5, V6, C1 or third-party models (Seedance, Kling, Veo 3.1, MiniMax H3, Wan 3.0); the first frame sets the aspect ratio. For three to seven frames use pixverse_create_transition; for one image, pixverse_create_video. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/create-frames.

Inputs: last_frame_path (required), first_frame_path (required), seed, wait, +10 more.

pixverse_create_video_fusionVideo from reference images, videos and audioAInspect

Generate a video from reference images (and, on models that take them, reference videos and audio) cited in the prompt as @image1, @video1, @audio1 (PixVerse's Reference mode), with V5 (default), V5.6, C1 or third-party models (Seedance, Kling 4.0 / O3, MiniMax H3, Wan 3.0, Gemini Omni Flash); each model takes its own number of references. Naming a model makes duration and quality required. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/create-fusion.

Inputs: prompt (required), seed, wait, audio, +12 more.

pixverse_delete_imageDelete an imageA
DestructiveIdempotent
Inspect

Delete one image from its PixVerse account by image_id (from pixverse_create_image, pixverse_get_image or pixverse_list_images). Videos and music videos are deleted with pixverse_delete_video. Cannot be undone. DELETE /images/{image_id}.

Inputs: image_id (required).

pixverse_delete_videoDelete a videoA
DestructiveIdempotent
Inspect

Delete one video from its PixVerse account by video_id (from a create tool, pixverse_get_video or pixverse_list_videos); music videos too (same video_id). Images: pixverse_delete_image. Cannot be undone. DELETE /videos/{video_id}.

Inputs: video_id (required).

pixverse_extend_videoExtend a videoAInspect

Continue a video from its last frame with v6 or grok-imagine: a PixVerse video (video_id, on its account) or your own upload (video_path). To change what is in a video use pixverse_modify_video. Uses PixVerse credits. Waits up to ~50 s, then returns the new video_id for pixverse_get_video. POST /videos/extend.

Inputs: seed, wait, audio, email, +8 more.

pixverse_get_accountGet an accountA
Read-onlyIdempotent
Inspect

One account's stored settings: email, maxJobs, the PixVerse session's expiry (jwt.ExpireTimeUTC) and any pending error (such an account answers 596 until it is added again). No call to PixVerse; use pixverse_get_features for the live plan and credits, pixverse_list_accounts for every account. GET /accounts/{email}.

Inputs: email (required).

pixverse_get_featuresGet plan and creditsA
Read-onlyIdempotent
Inspect

Read one account's PixVerse plan live: plan_name, credit balances (credit_daily, credit_monthly, credit_package and the gift credits), refresh and expiry dates, gen_simultaneously (generations at once) and the image models and video qualities the plan allows. Use before a paid generation; pixverse_get_account shows only the stored settings. GET /features.

Inputs: email.

pixverse_get_imageGet an imageA
Read-onlyIdempotent
Inspect

One image from pixverse_create_image, pixverse_upscale_image or pixverse_list_images: image_status_name (QUEUED, GENERATING, PROCESSING, COMPLETED, FAILED, MODERATED) and, once completed, image_url, size and cost_credits (0 for a Relax Mode image), with the image as an image block. wait: true waits up to ~50 s. GET /images/{image_id}.

Inputs: image_id (required), wait.

pixverse_get_musicGet a music trackA
Read-onlyIdempotent
Inspect

One track from pixverse_create_music or pixverse_list_music: audio_status_name (QUEUED, GENERATING, COMPLETED, FAILED) and, once completed, the mp3 url, duration and model; fail_reason when it failed. wait: true waits up to ~50 s. Speech clips are read with pixverse_get_speech. GET /music/{audio_id}.

Inputs: audio_id (required), wait.

pixverse_get_music_videoGet a music videoA
Read-onlyIdempotent
Inspect

One music video from pixverse_create_music_video: status (pending, processing, succeeded, failed), its settings and, once succeeded, the video (url, cover_url, size, duration) and extra files such as the copy without captions. wait: true waits up to ~50 s. Delete it with pixverse_delete_video. GET /music-video/{video_id}.

Inputs: video_id (required), wait.

pixverse_get_speechGet a speech clipA
Read-onlyIdempotent
Inspect

One speech clip from pixverse_create_speech or pixverse_list_speech: audio_status_name (QUEUED, GENERATING, COMPLETED, FAILED) and, once completed, the audio url, duration, voice and language; fail_reason when it failed. wait: true waits up to ~50 s. Music tracks are read with pixverse_get_music. GET /speech/{audio_id}.

Inputs: audio_id (required), wait.

pixverse_get_videoGet a videoA
Read-onlyIdempotent
Inspect

One video by video_id, from any create, extend, modify, lip-sync or upscale tool: video_status_name (QUEUED, GENERATING, COMPLETED, FAILED, MODERATED) and, once completed, url, size, duration, model and, for a Seedance 2.5 draft, seedance_draft (can_create_final, expires_at). PixVerse answers 404 while a video is still processing; wait: true waits up to ~50 s through that. GET /videos/{video_id}.

Inputs: video_id (required), wait.

pixverse_lipsync_videoLip-sync a videoAInspect

Make the person in a video speak, from your own audio (audio_path, up to 60 seconds) or from text (prompt) read by a voice from pixverse_list_lipsync_voices (speaker_id), with v5: a PixVerse video (video_id) or your own upload (video_path). Uses PixVerse credits. Waits up to ~50 s, then returns the new video_id for pixverse_get_video. POST /videos/lipsync.

Inputs: wait, email, model, prompt, +7 more.

pixverse_list_accountsList PixVerse accountsA
Read-onlyIdempotent
Inspect

List the PixVerse accounts added to this useapi.net API token, as stored: email, maxJobs, session expiry and any pending account error. No call to PixVerse; pixverse_get_features shows a live plan and credits. Accounts are added on the setup page, not here. GET /accounts.

Inputs: no named parameters.

pixverse_list_effectsList effect templatesA
Read-onlyIdempotent
Inspect

PixVerse's effect templates (more than 900) for pixverse_create_video's template_id: template_id, display_name, effect_type (how many input images), template_type (1 video, 2 image), the template's model, qualities, duration and example_text. search filters by name or prompt; a page at a time (offset, limit). GET /videos/effects.

Inputs: email, limit, offset, search.

pixverse_list_imagesList imagesA
Read-onlyIdempotent
Inspect

One account's PixVerse images, including those still queued or generating (made with the API or on pixverse.ai): image_id, status, prompt and image_url, a page at a time; pass next_offset as offset for the next page and follow has_more (a page can be shorter than limit). pixverse_get_image reads one image. GET /images.

Inputs: email, limit, offset.

pixverse_list_lipsync_voicesList lip-sync voicesA
Read-onlyIdempotent
Inspect

The voices for lip-sync speech: speaker_id, display_name and a sample url. Pass a speaker_id to pixverse_lipsync_video (speaker_id) or pixverse_create_video (lip_sync_tts_speaker_id, v5). Text-to-speech voices are a different list: pixverse_list_speech_voices. GET /videos/voices.

Inputs: email.

pixverse_list_musicList music tracksA
Read-onlyIdempotent
Inspect

One account's music tracks: audio_id, status, prompt, model and mp3 url, a page at a time; pass next_offset as offset for the next page while has_more. Speech clips are listed by pixverse_list_speech, music videos by pixverse_list_music_videos. GET /music.

Inputs: email, limit, offset.

pixverse_list_music_video_libraryList music video songs, characters and stylesA
Read-onlyIdempotent
Inspect

PixVerse's built-in songs (audio_path), characters (image_path) and styles (image_path) for pixverse_create_music_video, each with its name and url; type picks one group. Use them when you have no song or photo of your own (else pixverse_upload_file). GET /music-video/library.

Inputs: type, email.

pixverse_list_music_videosList music videosA
Read-onlyIdempotent
Inspect

One account's music videos: video_id, status, name and the finished video, a page at a time; pass next_offset as offset for the next page while has_more. pixverse_get_music_video reads one with its extra files. GET /music-video.

Inputs: email, limit, offset.

pixverse_list_running_jobsList running jobs and free slotsA
Read-onlyIdempotent
Inspect

The videos, images, music and speech the API is tracking now (id, type, started, elapsed) and, per account, maxJobs with its running and free slots. The first check when a create tool answers 429 (accounts at maxJobs); jobs started on pixverse.ai or in Off-Peak mode are not tracked (pixverse_list_videos shows them). GET /scheduler/available.

Inputs: no named parameters.

pixverse_list_speechList speech clipsA
Read-onlyIdempotent
Inspect

One account's speech clips: audio_id, status, voice, language and audio url, a page at a time; pass next_offset as offset for the next page while has_more. Music tracks are listed by pixverse_list_music. GET /speech.

Inputs: email, limit, offset.

pixverse_list_speech_modelsList text-to-speech modelsA
Read-onlyIdempotent
Inspect

The text-to-speech models by provider, live from PixVerse: model, display_name, max_characters, supported_language_codes and credit_formula (credits per unit of characters), plus default_model. Use it to pick a model and language_code for pixverse_create_speech; voices come from pixverse_list_speech_voices. GET /speech/models.

Inputs: email.

pixverse_list_speech_voicesList text-to-speech voicesA
Read-onlyIdempotent
Inspect

The text-to-speech voices of one model's provider for pixverse_create_speech: voice_id, display_name, gender, age, accent, recommended languages, preview_url and compatible_models; language narrows it to voices recommended for that language. A page at a time (offset, limit). Lip-sync voices are pixverse_list_lipsync_voices. GET /speech/voices.

Inputs: email, limit, model, offset, +1 more.

pixverse_list_videosList videosA
Read-onlyIdempotent
Inspect

One account's PixVerse videos, including those still queued or generating and music videos (made with the API or on pixverse.ai): video_id, status, prompt, model and url, a page at a time; pass next_offset as offset for the next page. pixverse_get_video reads one video. GET /videos.

Inputs: email, limit, offset.

pixverse_modify_videoModify a video by promptAInspect

Change what is in an existing video by a prompt, with v5.5, at 360p, 540p, 720p: a PixVerse video (video_id) or your own upload (video_path). To lengthen a video use pixverse_extend_video. Uses PixVerse credits by the video's length and quality. Waits up to ~50 s, then returns the new video_id for pixverse_get_video. POST /videos/modify.

Inputs: prompt (required), seed, wait, email, +6 more.

pixverse_motion_controlAnimate a character with a motion videoAInspect

Make the person or animal in a character image move like the subject of a reference video (PixVerse motion control, v5.6); no prompt. The image must show a clear subject (422 otherwise). Both are paths from pixverse_upload_file. Uses PixVerse credits by the motion video's length. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/motion-control.

Inputs: image_path (required), video_path (required), wait, email, +4 more.

pixverse_upload_fileUpload an image, video or audioAInspect

Upload your own image (PNG, JPEG, GIF, WebP; PixVerse does not support images above about 2048 px), video (MP4, MOV, WebM and more) or audio (WAV, MP3) for use as a reference, up to 50 MB here (larger files: POST /files directly). Send a public https url or contentBase64 (small files). Returns the file's path (and an image's id): pass the path as image_path, first_frame_path, video_path or audio_path of the create tools; it works on any of your accounts. There is no delete for uploads. POST /files.

Inputs: url, email, mimeType, contentBase64.

pixverse_upscale_imageUpscale an imageAInspect

Upscale a PixVerse image (image_id) or your own upload (image_path) with pixverse-upscale or topaz-gigapixel (default pixverse-upscale); quote: true answers the exact price in credits and creates nothing. Uses PixVerse credits (412 when the account has too few). Waits up to ~50 s, then returns the new image_id for pixverse_get_image. POST /images/upscale.

Inputs: wait, email, model, quote, +4 more.

pixverse_upscale_videoUpscale a videoAInspect

Upscale a PixVerse video (video_id) or your own MP4 / MOV upload (video_path, under 4K, up to 3 minutes) with pixverse-upscale, topaz-proteus, topaz-starlight-fast, topaz-starlight-precise (default pixverse-upscale); quote: true answers the exact price in credits and creates nothing. Credits per second of the video, by model and quality (412 when the account has too few). Waits up to ~50 s, then returns the new video_id for pixverse_get_video. POST /videos/upscale.

Inputs: wait, email, model, quote, +4 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources