convez.ai
MCP ServerEscrita & ConteúdoIntermediário
mcp-tool-shop-org

MCP Voice Soundboard

mcp-tool-shop-org/mcp-voice-soundboard

Text-to-speech MCP com 48 vozes, 9 idiomas e suporte a emoções

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP para síntese de fala com 48 vozes em 9 idiomas, suportando emoções, efeitos sonoros e diálogos multi-locutor. Inclui tags SSML-lite, presets curados e guardrails para controle de taxa e segurança.

Instalação

$npx convez-ai mcp-tool-shop-org/mcp-voice-soundboard

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
100%
Último commit
há 1 semana
Versão
v2.5.5
Issues abertas
6
Contribuidores
2

Casos de uso

  • Geração de áudio para conteúdo narrativo e storytelling
  • Criação de diálogos multi-locutor automatizados
  • Produção de anúncios e narrações com modulação de emoção

Veredito

Ferramenta robusta de TTS com suporte multilíngue e features avançadas (emoções, SFX, SSML-lite). Bem estruturada para integração em pipelines de conteúdo, embora o setup requeira familiaridade com MCP e Node.js.

README

A tradução para o português deste README ainda está na fila.


Highlights

  • MCP native — stdio transport, works with Claude Desktop, Cursor, and any MCP client
  • 5 tools — voice_speak, voice_dialogue, voice_status, voice_interrupt, voice_inner_monologue
  • 48 approved voices, 9 languages — English (American + British), Japanese, Mandarin, Spanish, French, Hindi, Italian, Brazilian Portuguese. Curated presets: narrator, announcer, whisper, storyteller, assistant
  • Emotion spans — 8 emotions via {joy}...{/joy} inline markup
  • SSML-lite — <break>, <emphasis>, <prosody> without full SSML complexity
  • SFX tags — [ding], [chime], [whoosh], [tada], [pop], [click] inline sound effects
  • Multi-speaker dialogue — Speaker: line format with auto-cast and pause directives
  • Guardrails — rate limiting, concurrency semaphore, request timeouts, path traversal protection, secret redaction
  • Swappable backends — Mock (built-in), HTTP proxy, Python bridge, or bring your own

Quick Start

npx @mcptoolshop/voice-soundboard-mcp

Or install globally:

npm install -g @mcptoolshop/voice-soundboard-mcp
voice-soundboard-mcp

Claude Desktop / MCP Client Config

Add to your MCP client configuration (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "voice-soundboard": {
      "command": "npx",
      "args": ["-y", "@mcptoolshop/voice-soundboard-mcp"]
    }
  }
}

With options:

{
  "mcpServers": {
    "voice-soundboard": {
      "command": "npx",
      "args": [
        "-y", "@mcptoolshop/voice-soundboard-mcp",
        "--artifact=path",
        "--output-dir=/tmp/voice-output",
        "--timeout=30000",
        "--max-concurrent=2"
      ]
    }
  }
}

MCP Tools

voice_speak

Synthesize speech from text.

text:         "Hello world!"
voice?:       "am_fenrir"          # Voice ID or preset name
speed?:       1.0                  # 0.5 - 2.0
mood?:        "dry"                # Humor mood (sensor-humor integration)
format?:      "wav"                # wav | mp3 | ogg | raw
artifactMode?: "path"             # path | base64
outputDir?:   "subdir"            # Subdirectory within output root
sfx?:         true                # Enable [ding], [chime] etc.

voice_dialogue

Multi-speaker dialogue synthesis.

script:       "Alice: Hello!\nBob: Hey there!"
cast?:        { "Alice": "af_sky", "Bob": "am_fenrir" }
speed?:       1.0
concat?:      true                 # Combine into single file
debug?:       true                 # Include cue_sheet
artifactMode?: "path"             # path | base64
outputDir?:   "subdir"            # Subdirectory within output root

voice_status

Returns engine health, available voices, presets, and backend info. No arguments.

voice_interrupt

Stop or rollback active synthesis.

streamId?:    "stream-123"
reason?:      "user_spoke"         # user_spoke | context_change | timeout | manual

voice_inner_monologue

Ephemeral micro-utterances for ambient narration. Requires --ambient flag or VOICE_SOUNDBOARD_AMBIENT_ENABLED=1.

text:         "Interesting..."     # Max 500 chars, auto-redacted
category?:    "thinking"           # general | thinking | observation | debug

Voices

48 voices across 9 languages. Language is auto-inferred from the voice ID prefix — no configuration required.

PrefixLanguage
af_ / am_English (American)
bf_ / bm_English (British)
jf_ / jm_Japanese
zf_ / zm_Mandarin Chinese
ef_ / em_Spanish
ff_French
hf_ / hm_Hindi
if_ / im_Italian
pf_ / pm_Brazilian Portuguese

English — American

IDNameGenderStyle
af_aoedeAoedeFemaleMusical
af_bellaBellaFemaleWarm
af_heartHeartFemaleCaring
af_jessicaJessicaFemaleProfessional
af_koreKoreFemaleYouthful
af_nicoleNicoleFemaleSoft
af_sarahSarahFemaleClear
af_skySkyFemaleAiry
am_ericEricMaleConfident
am_fenrirFenrirMalePowerful
am_liamLiamMaleFriendly
am_michaelMichaelMaleDeep
am_onyxOnyxMaleSmooth
am_puckPuckMalePlayful

English — British

IDNameGenderStyle
bf_aliceAliceFemaleProper
bf_emmaEmmaFemaleRefined
bf_isabellaIsabellaFemaleWarm
bm_fableFableMaleStorytelling
bm_georgeGeorgeMaleAuthoritative
bm_lewisLewisMaleFriendly

Japanese

IDNameGenderStyle
jf_alphaAlphaFemaleClear
jf_gongitsuneGongitsuneFemaleStorytelling
jf_nezukoNezukoFemaleGentle
jf_tebukuroTebukuroFemaleWarm
jm_kumoKumoMaleCalm

Mandarin Chinese

IDNameGenderStyle
zf_xiaobeiXiaobeiFemaleBright
zf_xiaoniXiaoniFemaleGentle
zf_xiaoxiaoXiaoxiaoFemaleClear
zf_xiaoyiXiaoyiFemaleWarm
zm_yunjianYunjianMaleAuthoritative
zm_yunxiYunxiMaleFriendly
zm_yunxiaYunxiaMaleCalm
zm_yunyangYunyangMaleConfident

Spanish

IDNameGenderStyle
ef_doraDoraFemaleWarm
em_alexAlexMaleConfident
em_santaSantaMaleJolly

French

IDNameGenderStyle
ff_siwisSiwisFemaleRefined

Hindi

IDNameGenderStyle
hf_alphaAlphaFemaleClear
hf_betaBetaFemaleWarm
hm_omegaOmegaMaleDeep
hm_psiPsiMaleCalm

Italian

IDNameGenderStyle
if_saraSaraFemaleWarm
im_nicolaNicolaMaleConfident

Brazilian Portuguese

IDNameGenderStyle
pf_doraDoraFemaleWarm
pm_alexAlexMaleConfident
pm_santaSantaMaleJolly

Presets

PresetVoiceSpeedDescription
narratorbm_george0.95Calm, clear, documentary style
announceram_eric1.1Bold, energetic, broadcast style
whisperaf_sky0.85Soft, intimate, gentle
storytellerbf_emma0.90Expressive, varied pacing
assistantaf_jessica1.0Friendly, helpful, conversational

Emotion Spans

Wrap text in emotion tags to control prosody and voice routing:

{joy}Great news!{/joy} But {calm}let me explain.{/calm}

Supported: neutral, serious, friendly, professional, calm, joy, urgent, whisper

CLI Flags

FlagDefaultDescription
--artifact=path|base64pathAudio delivery mode
--output-dir=<path><tmpdir>/voice-soundboard/Output directory
--backend=mock|http|pythonmockBackend selection
--ambientoffEnable inner-monologue system
--max-concurrent=<n>3Max concurrent synthesis requests
--timeout=<ms>60000Per-request timeout
--retention-minutes=<n>240Auto-cleanup age (0 to disable)

Packages

This is a pnpm monorepo with two publishable packages:

PackageDescriptionnpm
@mcptoolshop/voice-soundboard-coreBackend-agnostic core library (validation, SSML, chunking, schemas)npm
@mcptoolshop/voice-soundboard-mcpMCP server with CLI, guardrails, and transportnpm

Development

# Install
pnpm install

# Build
pnpm build

# Test (363 tests)
pnpm test

# Build + test in one step
pnpm verify

Part of MCP Tool Shop

Project Structure

mcp-voice-soundboard/
  packages/
    core/               @mcptoolshop/voice-soundboard-core
      src/
        limits.ts         SHIP_LIMITS, text/chunk limits
        schemas.ts        VoiceRequest, VoiceResponse, error codes
        artifact.ts       resolveOutputDir, path sandbox
        voices.ts         Approved voice registry + presets
        emotion.ts        Emotion span parser
        ssml/             SSML-lite parser + limits
        chunking/         Text chunker
        sfx/              SFX tag parser + registry
        sandbox.ts        Safe filenames, symlink checks
        ambient.ts        AmbientEmitter for inner monologue
        redact.ts         PII/secret redaction
    mcp-server/         @mcptoolshop/voice-soundboard-mcp
      src/
        server.ts         MCP tool registration + guardrail wiring
        cli.ts            CLI entrypoint (stdio transport)
        backend.ts        Backend abstraction + mock/HTTP
        concurrency.ts    SynthesisSemaphore
        rateLimit.ts      ToolRateLimiter (sliding window)
        timeout.ts        withTimeout utility
        retention.ts      Output file cleanup timer
        redact.ts         Server-level redaction
        validation.ts     Synthesis result validation
        tools/            Individual tool handlers
  assets/               Logo, audio event manifests
  docs/                 Architecture docs

Privacy

No telemetry. This tool collects no usage data, sends no analytics, and makes no network requests except to the TTS backend you configure. All processing is local.

Security

See SECURITY.md for vulnerability reporting.

See THREAT_MODEL.md for the full threat surface analysis.

Related

ProjectDescription
soundboard-pluginClaude Code plugin — slash commands, emotion-aware narration

Support

Scorecard

CategoryScoreNotes
A. Security10/10SECURITY.md, THREAT_MODEL.md, redaction, no telemetry
B. Error Handling8/10Structured error contract (code/hint/retryable), toToolError pattern
C. Operator Docs9/10README, CHANGELOG, HANDBOOK, tool docs
D. Shipping Hygiene9/10CI, verify script, dependabot, lockfile
E. Identity10/10Logo, translations, landing page, metadata
Total46/50

License

MIT


Ver o original no GitHub

Bom para

Relacionados