APICK

TTS 작업 접수

tts_jobs_create

한국어 TTS를 접수합니다. 기본 정규화 스킬이 발음을 다듬으며 추가 요금이 합산됩니다. normalize_text=false로 끌 수 있습니다. 완료 후 MP3와 원문 ASS를 공통 API로 받습니다. 서버 오류로 최종 실패하면 정규화까지 전액 환불하고, 연결 종료는 정상 과금합니다. [실제 사용량 기준(작업당 기본요금 5P) + 기본 on 정규화 스킬 요금]

Input Schema

Name	Required	Description
`pace`	No	말 속도 배율 0.5~2.0. 1이 기본
`text`	No	합성할 한국어 텍스트. utterances와 둘 중 하나
`tone`	No	용도·톤. 생략 시 기본
`pitch`	No	음높이 -12~12 반음. 0이 기본
`style`	No	자유 서술 낭독 스타일
`accent`	No	억양. 생략 시 표준어
`emotion`	No	감정 표현. 생략 시 기본
`speakers`	No	화자 이름 → {voice_id, style, emotion, tone, accent, pace, pitch, volume_gain_db}
`voice_id`	No	Gemini 목소리 ID. 기본 Kore. tts_gemini_voices에서 기본·확장 목록 조회
`utterances`	No	발화 목록. text와 둘 중 하나
`multi_speaker`	No	멀티화자. Gemini는 화자 2명까지 한 호출, ChatGPT는 발화별 목소리 대화
`normalize_text`	No	기본 true. 정규화 스킬 비용 합산, false는 실행·과금 생략
`volume_gain_db`	No	음량 보정 -12~12 dB. 0이 기본
`idempotency_key`	No	접수 응답 유실 시 같은 요청에 재사용할 키

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 5, 2026

addedInput schema / properties / style

Added value: +{
+  "description": "자유 서술 낭독 스타일",
+  "maxLength": 1000,
+  "type": "string"
+}

changedInput schema / properties / voice_id / description

Previous value: -"지원 voice_id"New value: +"Gemini 목소리 ID. 기본 Kore. tts_gemini_voices에서 기본·확장 목록 조회"

removedInput schema / properties / voice_id / enum

Removed value: -[
-  "Zephyr",
-  "Autonoe",
-  "Puck",
-  "Laomedeia",
-  "Charon",
-  "Rasalgethi",
-  "Kore",
-  "Orus",
-  "Alnilam",
-  "Fenrir",
-  "Leda",
-  "Aoede",
-  "Callirrhoe",
-  "Umbriel",
-  "Enceladus",
-  "Iapetus",
-  "Erinome",
-  "Algieba",
-  "Despina",
-  "Algenib",
-  "Achernar",
-  "Schedar",
-  "Gacrux",
-  "Pulcherrima",
-  "Achird",
-  "Zubenelgenubi",
-  "Vindemiatrix",
-  "Sadachbia",
-  "Sadaltager",
-  "Sulafat",
-  "alloy",
-  "ash",
-  "ballad",
-  "coral",
-  "echo",
-  "fable",
-  "onyx",
-  "nova",
-  "sage",
-  "shimmer",
-  "verse"
-]

addedInput schema / properties / voice_id / maxLength
```
Added value: +160
```
removedInput schema / required
```
Removed value: -[
-  "voice_id"
-]
```

Changed12 schema fields changedOct 5, 2026

addedInput schema / properties / accent

Added value: +{
+  "description": "억양. 생략 시 표준어",
+  "enum": [
+    "standard",
+    "seoul",
+    "gyeongsang",
+    "jeolla",
+    "chungcheong"
+  ],
+  "type": "string"
+}

addedInput schema / properties / emotion

Added value: +{
+  "description": "감정 표현. 생략 시 기본",
+  "enum": [
+    "neutral",
+    "calm",
+    "cheerful",
+    "excited",
+    "sad",
+    "serious",
+    "friendly",
+    "empathetic",
+    "confident",
+    "gentle",
+    "whisper",
+    "narration"
+  ],
+  "type": "string"
+}

removedInput schema / properties / fallback_options

Removed value: -{
-  "additionalProperties": {},
-  "description": "전환할 때만 적용하는 voice_id, style",
-  "propertyNames": {
-    "type": "string"
-  },
-  "type": "object"
-}

removedInput schema / properties / fallback_policy

Removed value: -{
-  "description": "기본 never. queue_full=대기열 포화, busy=즉시 실행 불가 시 Gemini 전환",
-  "enum": [
-    "never",
-    "queue_full",
-    "busy"
-  ],
-  "type": "string"
-}

addedInput schema / properties / multi_speaker

Added value: +{
+  "description": "멀티화자. Gemini는 화자 2명까지 한 호출, ChatGPT는 발화별 목소리 대화",
+  "type": "boolean"
+}

addedInput schema / properties / pace

Added value: +{
+  "description": "말 속도 배율 0.5~2.0. 1이 기본",
+  "type": "number"
+}

addedInput schema / properties / pitch

Added value: +{
+  "description": "음높이 -12~12 반음. 0이 기본",
+  "type": "number"
+}

addedInput schema / properties / speakers

Added value: +{
+  "additionalProperties": {},
+  "description": "화자 이름 → {voice_id, style, emotion, tone, accent, pace, pitch, volume_gain_db}",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

changedInput schema / properties / text / maxLength
```
Previous value: -800New value: +8000
```

addedInput schema / properties / tone

Added value: +{
+  "description": "용도·톤. 생략 시 기본",
+  "enum": [
+    "narration",
+    "news",
+    "audiobook",
+    "documentary",
+    "ad",
+    "conversation",
+    "announcement",
+    "tutorial",
+    "storytelling"
+  ],
+  "type": "string"
+}

changedInput schema / properties / voice_id / enum

Previous value: -[
-  "v2_ann_m_30s_01",
-  "v2_ann_m_30s_02",
-  "v2_ann_m_30s_04",
-  "v2_ann_m_30s_05",
-  "v2_ann_f_30s_02",
-  "v2_ann_f_30s_03",
-  "v2_ann_f_30s_04",
-  "v2_ann_f_30s_05",
-  "v2_m_teen_01",
-  "v2_m_young_01",
-  "v2_m_mid_01",
-  "v2_m_senior_01",
-  "v2_f_young_01",
-  "v2_f_senior_01"
-]New value: +[
+  "Zephyr",
+  "Autonoe",
+  "Puck",
+  "Laomedeia",
+  "Charon",
+  "Rasalgethi",
+  "Kore",
+  "Orus",
+  "Alnilam",
+  "Fenrir",
+  "Leda",
+  "Aoede",
+  "Callirrhoe",
+  "Umbriel",
+  "Enceladus",
+  "Iapetus",
+  "Erinome",
+  "Algieba",
+  "Despina",
+  "Algenib",
+  "Achernar",
+  "Schedar",
+  "Gacrux",
+  "Pulcherrima",
+  "Achird",
+  "Zubenelgenubi",
+  "Vindemiatrix",
+  "Sadachbia",
+  "Sadaltager",
+  "Sulafat",
+  "alloy",
+  "ash",
+  "ballad",
+  "coral",
+  "echo",
+  "fable",
+  "onyx",
+  "nova",
+  "sage",
+  "shimmer",
+  "verse"
+]

addedInput schema / properties / volume_gain_db

Added value: +{
+  "description": "음량 보정 -12~12 dB. 0이 기본",
+  "type": "number"
+}

Changed7 schema fields changedOct 4, 2026

addedInput schema / properties / fallback_options

Added value: +{
+  "additionalProperties": {},
+  "description": "전환할 때만 적용하는 voice_id, style",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

addedInput schema / properties / fallback_policy

Added value: +{
+  "description": "기본 never. queue_full=대기열 포화, busy=즉시 실행 불가 시 Gemini 전환",
+  "enum": [
+    "never",
+    "queue_full",
+    "busy"
+  ],
+  "type": "string"
+}

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "접수 응답 유실 시 같은 요청에 재사용할 키",
+  "maxLength": 128,
+  "pattern": "^[A-Za-z0-9_.:-]+$",
+  "type": "string"
+}

addedInput schema / properties / normalize_text

Added value: +{
+  "description": "기본 true. 정규화 스킬 비용 합산, false는 실행·과금 생략",
+  "type": "boolean"
+}

changedInput schema / properties / text / description

Previous value: -"합성할 한국어 텍스트 (최대 800자)"New value: +"합성할 한국어 텍스트. utterances와 둘 중 하나"

addedInput schema / properties / utterances

Added value: +{
+  "description": "발화 목록. text와 둘 중 하나",
+  "items": {},
+  "type": "array"
+}

changedInput schema / required

Previous value: -[
-  "voice_id",
-  "text"
-]New value: +[
+  "voice_id"
+]

Changed1 schema field changedOct 2, 2026

changedInput schema / properties / voice_id / enum

Previous value: -[
-  "v2_ann_m_30s_01",
-  "v2_ann_m_30s_02",
-  "v2_ann_m_30s_04",
-  "v2_ann_m_30s_05",
-  "v2_ann_f_30s_01",
-  "v2_ann_f_30s_02",
-  "v2_ann_f_30s_03",
-  "v2_ann_f_30s_04",
-  "v2_ann_f_30s_05",
-  "v2_m_teen_01",
-  "v2_m_young_01",
-  "v2_m_mid_01",
-  "v2_m_senior_01",
-  "v2_f_teen_01",
-  "v2_f_young_01",
-  "v2_f_senior_01"
-]New value: +[
+  "v2_ann_m_30s_01",
+  "v2_ann_m_30s_02",
+  "v2_ann_m_30s_04",
+  "v2_ann_m_30s_05",
+  "v2_ann_f_30s_02",
+  "v2_ann_f_30s_03",
+  "v2_ann_f_30s_04",
+  "v2_ann_f_30s_05",
+  "v2_m_teen_01",
+  "v2_m_young_01",
+  "v2_m_mid_01",
+  "v2_m_senior_01",
+  "v2_f_young_01",
+  "v2_f_senior_01"
+]

Changed1 schema field changedSep 20, 2026

changedInput schema / properties / voice_id / enum

Previous value: -[
-  "narrator_m_01",
-  "narrator_m_02",
-  "narrator_m_03",
-  "narrator_m_04",
-  "narrator_m_05",
-  "narrator_f_10s_01",
-  "narrator_f_10s_02",
-  "narrator_f_10s_03",
-  "narrator_m_20s_01",
-  "narrator_f_20s_01",
-  "narrator_f_20s_02",
-  "narrator_f_20s_03",
-  "narrator_f_20s_04",
-  "narrator_m_30s_01",
-  "narrator_m_30s_02",
-  "narrator_m_40s_01",
-  "narrator_m_80s_01"
-]New value: +[
+  "v2_ann_m_30s_01",
+  "v2_ann_m_30s_02",
+  "v2_ann_m_30s_04",
+  "v2_ann_m_30s_05",
+  "v2_ann_f_30s_01",
+  "v2_ann_f_30s_02",
+  "v2_ann_f_30s_03",
+  "v2_ann_f_30s_04",
+  "v2_ann_f_30s_05",
+  "v2_m_teen_01",
+  "v2_m_young_01",
+  "v2_m_mid_01",
+  "v2_m_senior_01",
+  "v2_f_teen_01",
+  "v2_f_young_01",
+  "v2_f_senior_01"
+]

First observedSep 6, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false). The description adds substantial value beyond them: default-on normalization with surcharge, how to disable it (normalize_text=false), full refund on server-error final failure, and normal billing on connection termination. This billing/refund behavior is exactly the kind of context annotations cannot carry.

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?

Content is dense and front-loaded with the core action and the normalization default. The trailing bracketed pricing formula ('[실제 사용량 기준...]') repeats cost information already stated earlier, a minor redundancy, but overall the sentences earn their place.

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 14-parameter, nested-object mutation with no output schema, the description covers billing, refund semantics, output retrieval, and the normalization toggle. The main gap is sibling differentiation against the other TTS create tools, but the operational behavior needed to call it correctly is well covered.

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 coverage is 100%, so the schema already documents all 14 parameters including normalize_text's cost implication. The description's mention of normalize_text=false mostly repeats what the schema property already states, adding little beyond the baseline for a fully-documented 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?

The description opens with a specific verb+resource: submitting a Korean TTS job ('한국어 TTS를 접수합니다'). It also states the two output formats (MP3, original ASS). However, it never distinguishes itself from the provider-specific siblings tts_gemini_create and tts_openai_create, so an agent cannot tell from the description which create-tool to pick.

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

Usage Guidelines3/5

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

'완료 후 MP3와 원문 ASS를 공통 API로 받습니다' implies the async submit-then-poll workflow (status/result siblings), and the normalize_text toggle is explained. But there is no explicit when-to-use-this vs tts_gemini_create/tts_openai_create/tts_quote routing guidance, leaving the main selection decision to inference.

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

All APICK tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TTS 작업 접수

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources