Skip to main content
Glama

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

Create speech

minimax_create_speech

Convert text to speech with a MiniMax voice (speech-2.8-hd, speech-2.8-turbo, speech-2.6-hd, speech-2.6-turbo, speech-2.5-hd-preview, speech-2.5-turbo-preview, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo; default speech-2.8-hd), up to 5000 characters on -hd models and 10000 on -turbo. voice_id comes from minimax_list_voices (built-in or cloned with minimax_clone_voice); emotion and language_boost values from minimax_get_speech_config. Billed per character in the account's MiniMax Audio credits (the subscription music uses, not Hailuo video credits; 412 without them); too many at once on an account answers 429. Waits up to ~50 s and returns the audioId and, once done, audio_url; else call minimax_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": "minimax_create_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
volNoVolume, 1 or more (default 1).
textYesThe words to speak, 1-5000 characters on -hd models, up to 10000 on -turbo. Supports MiniMax's inline markup for emotion, sounds and pauses (see the POST speech/create docs page).
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
modelNoDefault speech-2.8-hd. -turbo models take longer text and use fewer credits per character.
pitchNoPitch, -12 to 12 (default 0).
speedNoPlayback rate, 0.5-2 (default 1).
accountNoThe MiniMax account id (minimax_list_accounts) to generate on (a cloned voice_id picks its own account). Required when you have several MiniMax accounts; with one it may be left out.
emotionNoDefault Auto. A value from t2a_emotion of minimax_get_speech_config; or leave it out and mark up the text.
roboticNoEffect switch (default false).
replyRefNoOptional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters.
replyUrlNoOptional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters.
voice_idYesA voice_id from minimax_list_voices: a MiniMax voice id, or the voice_id of a cloned voice (that voice's account is used).
nasal_crispNoVoice effect, -100 to 100 (default 0).
spacious_echoNoEffect switch (default false).
deepen_lightenNoVoice effect, -100 to 100 (default 0).
language_boostNoBias pronunciation toward one language (default Auto): a language name from minimax_get_speech_config (voice_tag_language).
lofi_telephoneNoEffect switch (default false).
auditorium_echoNoEffect switch (default false).
stronger_softerNoVoice effect, -100 to 100 (default 0).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing billing semantics (per-character, MiniMax Audio credits not Hailuo video credits), the 412 failure mode when credits are absent, 429 on concurrency, and the ~50 s blocking window. It also states what is returned (audioId and, when finished, audio_url), which annotations alone cannot convey.

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?

Dense but front-loaded: capability, model list, prerequisites, billing, and return shape arrive in that order with no filler sentences. The one inefficiency is enumerating all ten model names, which duplicates the schema enum verbatim and could have been summarized.

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

Completeness5/5

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

For a 19-parameter mutation tool with no output schema, the description still covers return values, the blocking-versus-async contract, failure codes, and where dependent parameter values come from. An agent can call this correctly and handle the incomplete-result case without reading anything else.

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

Parameters3/5

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

Schema description coverage is 100%, so every one of the 19 parameters is already documented in the schema, including the model enum, character limits, and cross-tool sourcing for voice_id/emotion/language_boost. The description largely restates that same information rather than adding new syntax or format guidance, so the baseline 3 applies.

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 specific verb+resource ('Convert text to speech') and immediately scopes it to a MiniMax voice, then names the exact endpoint (POST /speech/create). It is unambiguously distinguishable from minimax_get_speech, minimax_list_speech, and minimax_create_music, all of which appear in the sibling list.

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

Usage Guidelines5/5

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

Explicitly routes prerequisites to the right siblings ('voice_id comes from minimax_list_voices... emotion and language_boost values from minimax_get_speech_config') and names the fallback path ('else call minimax_get_speech') when the wait expires. It also states the account-selection rule (a cloned voice_id picks its own account).

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