Skip to main content
Glama
CantoneseTTS.com MCP Server

CantoneseTTS.com MCP Server

Official
by cantonesetts

CantoneseTTS.com MCP Server (cantonesetts-mcp)

Official Model Context Protocol (MCP) connector for CantoneseTTS.com — the Hong Kong Cantonese AI Voiceover, Konglish & Frame-Synced .SRT Subtitle Studio.

Save 45 minutes per video on written-to-spoken Hong Kong Cantonese script rewriting (書面語轉地道口語), 7-emotion vocal directing, and CapCut / Premiere Pro .SRT + .VTT subtitle timeline alignment.


Available MCP Tools

  1. synthesize_cantonese_tts — Synthesize authentic Hong Kong Cantonese & Konglish speech with 7-emotion directing (happy, sad, angry, fearful, disgusted, surprised, neutral), returning a clean .mp3 URL plus frame-aligned .srt and .vtt subtitles.

  2. list_cantonese_voices — List all 19 curated Hong Kong Cantonese, Konglish bilingual, and Studio VIP 3-track signature voices.

  3. check_character_wallet — Inspect real-time PostgreSQL character wallet balance and plan tier.


Related MCP server: audio.ditto/tts

Quick Setup

Option A: Direct Remote Streamable HTTP (Claude Code / Cursor / Windsurf)

{
  "mcpServers": {
    "cantonesetts": {
      "type": "http",
      "url": "https://cantonesetts.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ct_live_YOUR_STUDIO_VIP_KEY"
      }
    }
  }
}

Option B: Local Zero-Dependency STDIO Bridge (npx)

{
  "mcpServers": {
    "cantonesetts": {
      "command": "npx",
      "args": ["-y", "cantonesetts-mcp"],
      "env": {
        "CANTONESETTS_API_KEY": "ct_live_YOUR_STUDIO_VIP_KEY"
      }
    }
  }
}

License

MIT — see LICENSE.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables text-to-speech synthesis and voice cloning through GPT-SoVITS API integration. Supports multiple languages (Chinese, English, Japanese, Korean, Cantonese), dynamic model switching, and reference audio-based voice quality replication.
      4
      -
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI clients to browse voices and languages and synthesize text into downloadable audio links, including batch jobs of up to 1,000 texts.
      1
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI clients to turn text into synthesized speech through a remotely hosted GPT-SoVITS model, returning a signed, time-limited audio link that can be played or downloaded. Supports Chinese and English text with your own reference audio for voice and tone.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to manage voices and generate speech, multi-character dubbing, and batch audio through a local TTS service, including health checks and job polling.
      Apache 2.0