Skip to main content
Glama

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

Lip-sync a video

pixverse_lipsync_video

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.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pixverse_lipsync_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
emailNoThe account email, used only with video_path.
modelNoDefault v5.
promptNoText to speak instead of audio_path.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
video_idNoThe video_id of a PixVerse video (pixverse_list_videos, a create tool); its account is used, e.g. user:12345-pixverse:you@example.com-video:123456789 (it names the account).
audio_pathNoThe speech audio (up to 60 s): a path from pixverse_upload_file.
speaker_idNoThe voice for prompt: a speaker_id from pixverse_list_lipsync_voices.
video_pathNoOr your own video: a path from pixverse_upload_file.
off_peak_modeNotrue runs it in Off-Peak mode at a lower credit cost (native PixVerse models; the discount depends on the plan). Such a job is not waited for: read it later with pixverse_get_video.
original_sound_switchNotrue keeps the video's own soundtrack under the new speech.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the safety profile (not read-only, open-world, non-idempotent, non-destructive). The description adds real value beyond that: credit consumption, a ~50 s wait window, the returned video_id, and the important exception that off-peak jobs are never waited on. It leaves unstated whether the source video is altered versus a new asset being created.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The input mode and source choices are front-loaded before cost/latency details, which is the right ordering. The writing is dense — the first sentence packs many parenthetical clauses — but each clause carries information and the trailing endpoint note is short.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter asynchronous generation tool with no output schema, the description covers the trigger, the cost, the wait/poll contract, and the follow-up tool. Minor gaps remain: no guidance on what happens if neither audio nor prompt is supplied (all params are optional) and no mention of failure handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by pairing parameters (prompt needs a speaker_id from pixverse_list_lipsync_voices, audio_path is the alternative, video_path requires email) that the schema documents individually but does not relate to each other.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a concrete verb+resource ('Make the person in a video speak') and immediately enumerates the two input modes (audio_path vs. prompt+speaker_id) and the two video sources (video_id vs. video_path). This is specific enough to distinguish it from siblings like pixverse_create_speech and pixverse_create_video.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent which prerequisite tools to call first (pixverse_list_lipsync_voices for speaker_id, pixverse_get_video for the result) and names the alternative input routes. It stops short of explicit exclusions, e.g. when to prefer pixverse_create_speech over lip-sync, so it doesn't reach a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources