Skip to main content
Glama

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

Generate speech

pixverse_create_speech

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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>",
      "voice_id": "<voice_id>"
    },
    "name": "pixverse_create_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe words to speak (audio tags work on eleven-v3).
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
emailNoThe PixVerse account email (pixverse_list_accounts). Optional: by default a random account with a free slot.
modelNoDefault speech-2.8-hd.
pitchNoMiniMax only: pitch in semitones, -12 to 12.
speedNoSpeaking speed: 0.5-2 on MiniMax, 0.7-1.2 on ElevenLabs.
styleNoeleven-multilingual-v2 only: 0-1.
volumeNoMiniMax only: loudness, 0-10.
emotionNoMiniMax only: the emotion.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
voice_idYesA voice_id from pixverse_list_speech_voices.
stabilityNoElevenLabs only: 0-1 (default 0.5).
language_codeNoA language code the model supports (pixverse_list_speech_models); refused by eleven-v3.
similarity_boostNoElevenLabs only: 0-1 (default 0.75).
use_speaker_boostNoeleven-multilingual-v2 only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, open-world creation call, so the safety profile is covered. The description adds genuinely useful context beyond that: credit consumption billed per character, per-model setting refusal, and the ~50 s wait before returning an audio_id. That is solid added value, though return payload shape and failure behavior remain unstated, keeping it at a 3.

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?

Front-loads the core purpose and is dense with facts, but the model/limit list is delivered as a long semicolon run that takes a careful read to parse. Nearly every clause earns its place; only light restructuring would help.

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 a 15-parameter creation tool with no output schema, the description covers model selection, parameter compatibility, cost, blocking behavior, and the follow-up tool for retrieving results. It never explains what happens to the job or credits on failure, which would complete the picture.

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 baseline is 3, but the description adds meaning the schema lacks: which model families are MiniMax vs ElevenLabs, the per-model character ceilings (5,000-40,000) that the schema only caps globally at 40,000, and the fact that incompatible settings are refused rather than ignored.

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?

States a specific verb and resource ("Text-to-speech") and enumerates the exact models available with their character limits, which no sibling tool offers. An agent can distinguish this from pixverse_create_music or pixverse_create_music_video without opening the schema.

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?

Gives concrete routing: voice_id must come from pixverse_list_speech_voices, the resulting audio_id is consumed by pixverse_get_speech, and model/cost details point to pixverse_list_speech_models. It does not state when to prefer another generation tool (e.g. music vs speech), but the usage context here is clear.

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