Skip to main content
Glama
elibarnett

kie-mcp

by elibarnett
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

generate_tts

Generate speech from text using ElevenLabs via kie.ai. Supports Turbo 2.5 (fast) and Multilingual V2 (high quality). Downloads to kie/assets/raw/.

Instructions

Generate speech from text using ElevenLabs via kie.ai. Supports Turbo 2.5 (fast) and Multilingual V2 (high quality). Downloads to kie/assets/raw/.

Input Schema

NameRequiredDescriptionDefault
textYesText to synthesize into speech
waitNoSet false to submit and return immediately with the task_id (async mode) — then poll with check_task and fetch with download_result. Recommended for long generations to avoid client-side watchdog timeouts.
modelNoturbo-2-5=fast, multilingual-v2=high quality with language supportturbo-2-5
speedNoSpeech speed (0.7–1.2). Only for multilingual-v2.
filenameNoOutput filename. Auto-generated if omitted.
voice_idNoVoice name (e.g. "Bella", "Viking Bjorn", "Aria") or kie voice ID. kie.ai only accepts its curated ~67-voice set — arbitrary ElevenLabs voice IDs are rejected. An unknown value returns the full catalog. Optional — defaults to James.
max_creditsNoRefuse to submit if the estimated cost exceeds this many credits (overrides KIE_MAX_CREDITS_PER_CALL). Estimates come from published rates; kie bills the actual amount.
download_dirNoAbsolute directory to save the file(s) into (created if missing). Defaults to the server's kie/assets/raw/. Must be absolute — the MCP server's working directory is not the caller's.
estimate_onlyNoReturn the estimated credit cost WITHOUT submitting anything. Use before expensive runs (video, 4K, 1080p upgrades, layer splits).
language_codeNoLanguage code for multilingual-v2 (e.g. "en", "es", "fr", "ja")
max_wait_secondsNoOverride the blocking-mode polling budget in seconds (defaults: image 600, video 900, audio 300, speech 300). Ignored when wait=false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.8.0
    • addedInput schema / properties / estimate_only
      Added value: +{
+  "description": "Return the estimated credit cost WITHOUT submitting anything. Use before expensive runs (video, 4K, 1080p upgrades, layer splits).",
+  "type": "boolean"
+}
    • addedInput schema / properties / max_credits
      Added value: +{
+  "description": "Refuse to submit if the estimated cost exceeds this many credits (overrides KIE_MAX_CREDITS_PER_CALL). Estimates come from published rates; kie bills the actual amount.",
+  "type": "number"
+}
  2. First observedv4.7.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It does add real behavioral context — the file is written to kie/assets/raw/ (a local side effect) and calls are routed through kie.ai — but it omits cost/credit implications, blocking-vs-async behavior, and failure modes that an agent needs before invoking an 11-parameter generation tool.

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?

Two short sentences, front-loaded with the purpose, no filler. The trailing download-path sentence partly duplicates the download_dir schema default, which is the only minor redundancy.

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

Completeness3/5

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

For an 11-parameter generation tool with no output schema, the description leaves out cost expectations, output/variant behavior, and routing against the gemini TTS sibling. The rich schema compensates for parameter-level gaps, but the description is only minimally complete.

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 parameter is already self-documented; the baseline is 3. The description only restates the two model names (already the enum) and the download location, adding essentially nothing semantic beyond the schema.

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

Purpose4/5

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

States a concrete verb+resource ("Generate speech from text") and pins the provider stack (ElevenLabs via kie.ai), which implicitly separates it from the sibling generate_gemini_tts. However, it never names that sibling or any other alternative, so the differentiation must be inferred rather than read.

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

Usage Guidelines2/5

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

The description gives no when-to-use guidance: nothing explains when an agent should pick this over generate_gemini_tts, generate_dialogue, or generate_music. Model selection (turbo vs multilingual) is present but that is configuration, not usage routing.

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

Deploy Server

Other Tools