Supertone TTS MCP
@supertone-inc
MCP server for the Supertone TTS API. Generate natural speech, browse and preview the
Overview
What is Supertone TTS MCP?
A composable MCP toolkit for the Supertone TTS API. It exposes Supertone's SDK as a set of building-block tools — synthesis, voice discovery, preview, duration/credit prediction, usage tracking, and full voice-cloning CRUD — that an LLM assembles to fulfill a request. Works in Claude Desktop, Cursor, or any MCP‑compatible client.
How to use Supertone TTS MCP?
Install with uvx supertone-mcp or pip install supertone-mcp. Set SUPERTONE_API_KEY in your environment, then add the server to your MCP client config (e.g., claude_desktop_config.json). The LLM chains tools like search_voice, preview_voice, predict_duration, and text_to_speech to complete natural‑language requests.
Key features of Supertone TTS MCP
- Synthesis with
text_to_speechand per‑call controls - Voice discovery via
search_voice,get_voice,preview_voice - Custom voice cloning with full CRUD operations
- Duration and credit prediction without synthesizing
- Usage tracking and credit balance tools
- Streaming and autoplay support
Use cases of Supertone TTS MCP
- Discover a calm Korean female voice, preview a sample, estimate credit cost, then synthesize an announcement as MP3.
- Clone a voice from a local WAV file, then immediately use it for streaming speech with autoplay.
- Search the full voice catalog with no filters to list all available voices.
FAQ from Supertone TTS MCP
What is the default model?
The default model is sona_speech_2_flash. It changed from sona_speech_1 in version 0.2.0.
How do I set the output mode?
Pass the output_mode parameter to text_to_speech. Options are files (default), resources (inline audio), or both.
Can I stream synthesis?
Yes. Set streaming=true in text_to_speech, but this parameter is only supported with model="sona_speech_1".
Is autoplay enabled by default?
No. Autoplay defaults to false since version 0.2.0. Pass autoplay=true per call to play audio locally after synthesis.
What languages are supported?
31 languages are supported, including Korean, English, and Japanese.
