Skip to main content
Glama
BlockRunAI

BlockRun MCP

Official
by BlockRunAI
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

blockrun_speech

Generate speech from text or create custom sound effects using AI voice models. Select from ElevenLabs and ByteDance voices, adjust speed and output format, and pay per call.

Instructions

AI voice via BlockRun x402 — speak text aloud (ElevenLabs or ByteDance Seed Audio), generate sound effects, list voices.

Actions:

  • speak (default): text-to-speech. E.g. "speak this with the sarah voice". Price = chars/1000 × rate (min $0.001), quoted before payment.

  • sound_effect: cinematic sound effects from a text prompt, up to 22s ($0.0525/clip)

  • voices: list available voices (free)

Models (speak): elevenlabs/flash-v2.5 ($0.05/1k chars, 75ms, default), elevenlabs/turbo-v2.5 ($0.05/1k), elevenlabs/multilingual-v2 ($0.10/1k, narration), elevenlabs/v3 ($0.10/1k, most expressive), bytedance/seed-audio-1.0 ($0.003/sec of output, est. from input length; max 3k chars in / 120s out) — prompt-DIRECTED audio: describe the voice, emotion, and sound staging in the input text itself ("a tired detective mutters, rain in the background: ..."); the voice parameter is ignored.

Voice aliases (ElevenLabs models only): sarah (default), george, laura, charlie, river, roger, callum, harry — or any raw ElevenLabs voice_id.

Returns a hosted audio URL — download immediately if you need to keep the file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputNospeak: text to synthesize. sound_effect: description of the sound, e.g. 'rain on a tin roof, distant thunder' (max 1000 chars).
modelNoSpeech model (speak only). seed-audio-1.0 is prompt-directed: voice/emotion/staging go in the input text, the voice param is ignored, and billing is per estimated second of output.elevenlabs/flash-v2.5
speedNoPlayback speed 0.7-1.2 (speak only)
voiceNoVoice alias (sarah, george, laura, charlie, river, roger, callum, harry) or raw ElevenLabs voice_id. Default: sarah.
actionNospeak: text-to-speech (default). sound_effect: generate a sound effect. voices: list voices (free).speak
agent_idNoAgent identifier for budget tracking and enforcement.
response_formatNoAudio formatmp3
duration_secondsNoSound effect length in seconds (sound_effect only; default: auto)
prompt_influenceNoHow literally to follow the prompt, 0-1 (sound_effect only)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changedv0.45.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. Changed2 schema fields changedv0.40.1
    • changedInput schema / properties / model / description
      Previous value: -"Speech model (speak only)"New value: +"Speech model (speak only). seed-audio-1.0 is prompt-directed: voice/emotion/staging go in the input text, the voice param is ignored, and billing is per estimated second of output."
    • changedInput schema / properties / model / enum
      Previous value: -[
-  "elevenlabs/flash-v2.5",
-  "elevenlabs/turbo-v2.5",
-  "elevenlabs/multilingual-v2",
-  "elevenlabs/v3"
-]New value: +[
+  "elevenlabs/flash-v2.5",
+  "elevenlabs/turbo-v2.5",
+  "elevenlabs/multilingual-v2",
+  "elevenlabs/v3",
+  "bytedance/seed-audio-1.0"
+]
  3. Addedv0.22.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only indicate readOnlyHint=false and destructiveHint=false, so the description carries the burden of behavioral disclosure. It goes far beyond annotations by specifying pricing, per-model latency and characteristics, the prompt-directed behavior of bytedance/seed-audio-1.0 (voice parameter ignored), and that the returned hosted URL requires immediate download. This is rich, non-obvious behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence delivers useful information: purpose, actions, pricing, models, aliases, behavioral caveats, and return-value guidance. It is logically organized with line breaks and no filler, making it dense yet easy to scan.

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 9 parameters, 3 enums, no output schema, and minimal annotations, the description is remarkably complete. It covers return value behavior, pricing, model selection, voice handling, parameter constraints, and action differences—everything an agent needs to invoke the tool correctly.

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

Parameters5/5

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

Although schema description coverage is 100%, the description adds substantial meaning: it expands the voice aliases, explains when the voice param is ignored, gives model-specific billing details, clarifies action-specific parameter usage, and describes the output as a hosted audio URL. This far exceeds the baseline for fully covered schemas.

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 description clearly states the tool's core purpose: 'AI voice via BlockRun x402 — speak text aloud (ElevenLabs or ByteDance Seed Audio), generate sound effects, list voices.' It enumerates distinct actions, models, and voice aliases, giving agents a concrete understanding of what the tool does and how it differs from non-speech siblings like image, music, or video tools.

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?

The description provides clear action-level guidance: use 'speak' for text-to-speech, 'sound_effect' for cinematic effects, and 'voices' to list voices. It does not explicitly name sibling tools to contrast with, so while the usage context is strong, it lacks the explicit when-not-to-use-alternative statements that would earn a 5.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/BlockRunAI/blockrun-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server