Blackwood State

Text to speech

blackwood_speech_synthesize

Read-onlyIdempotent

Use when you need text to speech, tts, a voice audio file or spoken narration of a short text. Do not use for voice cloning, a chosen voice, SSML or audio longer than about two minutes. Returns JSON with text to speech (TTS): your text read aloud as WAV voice audio (base64, 44.1 kHz mono) by MeloTTS on Workers AI, in English, Spanish, French, Chinese, Japanese or Korean for 0.023 USDC per call. Typical response time 8000 ms (p95). Category: Media.

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>"
    },
    "name": "blackwood_speech_synthesize"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Speech language: en (default), es, fr, zh, ja or ko
`text`	Yes	Text to read aloud, e.g. Welcome to our store (up to 1000 characters)
`response_format`	No	concise (the default when omitted) keeps the JSON short: long fields such as base64 images or audio come back as separate image/audio content blocks and other long strings are cut with a marker; detailed returns the full JSON

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026

changedOutput schema / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "audioBase64": {
-        "type": "string"
-      },
-      "bytes": {
-        "type": "number"
-      },
-      "chars": {
-        "type": "number"
-      },
-      "lang": {
-        "type": "string"
-      },
-      "mimeType": {
-        "enum": [
-          "audio/wav",
-          "audio/mpeg"
-        ],
-        "type": "string"
-      },
-      "model": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "mimeType",
-      "audioBase64",
-      "bytes",
-      "lang",
-      "chars",
-      "model"
-    ],
-    "type": "object"
-  },
-  {
-    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
-    "properties": {
-      "accepts": {
-        "items": {
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "error": {
-        "type": "string"
-      },
-      "extensions": {
-        "type": "object"
-      },
-      "resource": {
-        "type": "object"
-      },
-      "x402Version": {
-        "type": "integer"
-      }
-    },
-    "required": [
-      "x402Version",
-      "accepts"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "audioBase64": {
+        "type": "string"
+      },
+      "bytes": {
+        "type": "number"
+      },
+      "chars": {
+        "type": "number"
+      },
+      "lang": {
+        "type": "string"
+      },
+      "mimeType": {
+        "enum": [
+          "audio/wav",
+          "audio/mpeg"
+        ],
+        "type": "string"
+      },
+      "model": {
+        "type": "string"
+      },
+      "next": {
+        "additionalProperties": false,
+        "description": "Suggested next paid call in the same family (call it in a loop when the task continues)",
+        "properties": {
+          "method": {
+            "enum": [
+              "GET",
+              "POST"
+            ],
+            "type": "string"
+          },
+          "sample": {
+            "description": "Free fixed sample of the whole family",
+            "type": "string"
+          },
+          "service": {
+            "description": "Service id of the suggested next paid call",
+            "type": "string"
+          },
+          "tool": {
+            "description": "MCP tool name of the same call",
+            "type": "string"
+          },
+          "url": {
+            "description": "Paid route of the next call",
+            "type": "string"
+          },
+          "useWhen": {
+            "description": "When the next call is the right one",
+            "type": "string"
+          }
+        },
+        "required": [
+          "service",
+          "tool",
+          "method",
+          "url",
+          "useWhen",
+          "sample"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "mimeType",
+      "audioBase64",
+      "bytes",
+      "lang",
+      "chars",
+      "model"
+    ],
+    "type": "object"
+  },
+  {
+    "description": "x402 PaymentRequired (returned with isError when payment is needed)",
+    "properties": {
+      "accepts": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "error": {
+        "type": "string"
+      },
+      "extensions": {
+        "type": "object"
+      },
+      "resource": {
+        "type": "object"
+      },
+      "x402Version": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "x402Version",
+      "accepts"
+    ],
+    "type": "object"
+  }
+]

AddedOct 17, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: the backing model (MeloTTS on Workers AI), output format and sample rate (base64 WAV, 44.1 kHz mono), the per-call cost (0.023 USDC) and the p95 latency (8000 ms). That is exactly the operational context an agent needs to decide whether to spend a call.

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 structure is well front-loaded: purpose, then exclusions, then return/pricing facts. It is a single dense block with some keyword-list padding ('text to speech, tts, a voice audio file or spoken narration'), but nearly every clause carries decision-relevant information.

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?

Given an output schema exists, return values need not be re-explained, yet the description still states format, languages, cost and latency. Combined with the exclusion list and the 1000-character schema bound, an agent has everything needed to call this correctly.

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%, with enums documented for lang and response_format, so the schema already carries parameter meaning and the baseline is 3. The description reinforces the language list and the short-text constraint but adds no syntax or default behavior beyond the schema.

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?

The opening sentence states a specific capability (text to speech / spoken narration of short text) with concrete synonyms an agent might match against, and the sibling blackwood_audio_transcribe is implicitly separated by the 'audio file out' vs transcription direction. An agent can identify the tool's output (WAV voice audio) 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 Guidelines5/5

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

It gives explicit use triggers ('text to speech, tts, a voice audio file or spoken narration') and explicit exclusions ('not for voice cloning, a chosen voice, SSML, or audio longer than about two minutes'), which routes the agent away from unsupported requests. The length ceiling and language set give practical boundary conditions for choosing this tool.

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

All Blackwood State 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.

Resources

Need Help?