Supertone TTS MCP
@supertone-inc
About Supertone TTS MCP
MCP server for the Supertone TTS API. Generate natural speech, browse and preview the
Basic information
Category
Other
Transports
stdio
Publisher
supertone-inc
Submitted by
(SUP_Engineering팀) 윤필립/Felix/Youn Pillip
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"supertone-tts": {
"command": "uvx",
"args": [
"supertone-mcp"
],
"env": {
"SUPERTONE_API_KEY": "your-api-key-here"
}
}
}
}Tools
14Generate natural-sounding speech audio from text. Use this when the user wants to: hear text read aloud, create narration or voiceover, generate voice audio, preview how text sounds when spoken, or convert any writing into spoken audio. Supports 31 languages including Korean, English, and Japanese. There is no text-length limit: long text is automatically split (auto-chunked) by the service, and credit usage and latency scale with the length of the text. Set output_mode ('files', 'resources', or 'both') to control how audio is returned, and autoplay=true to play it back on macOS. These per-call parameters REPLACE the removed SUPERTONE_MCP_OUTPUT_MODE and SUPERTONE_MCP_AUTOPLAY environment variables; autoplay now defaults to false. A default voice is already configured -- just call this tool directly. Only call search_voice if the user explicitly asks to change or browse voices.
Search the Supertone voice catalog. Filters are optional and combined with AND semantics: name, description, language, gender, age, use_case, style, model. With no filters, returns the full catalog (the v0.1 list_voices behavior). The output is a numbered plain-text list; when any filter is set, the first line shows "Filters applied: ...".
Fetch full detail for a single voice by voice_id. Returns name, description, age, gender, use_cases, languages, styles, supported models, sample count, and thumbnail URL. Use preview_voice to get the actual sample audio URLs.
Returns the remaining Supertone credit balance for the current API key. Use this before long TTS calls to confirm you have enough characters left.
Fetch sample audio URLs for a voice. Optionally filter samples by language, style, and model. Returns one URL per matching sample. v0.2 does NOT play the audio locally; pass the URL to your client to listen.
Predict the expected output audio duration in seconds for a given text WITHOUT producing any audio file. Accepts the same parameters as text_to_speech. There is no text-length limit: long text is automatically split (auto-chunked), and credit usage and latency scale with the length of the text. Use this to estimate credit cost before synthesizing — credit usage is proportional to the predicted duration.
Create a custom voice from a single local audio file. Constraints: WAV or MP3 only, max 3MB, exactly one file. The returned voice_id can be used immediately in text_to_speech. Path supports ~ expansion (e.g., "~/sample.wav").
List custom (cloned) voices created by this API key. Optional name and description filters perform partial matching. Pagination is handled internally; v0.2 returns the SDK default page.
Update the name and/or description of an existing custom voice. At least one of name or description must be provided.
Permanently delete a custom (cloned) voice. THIS IS IRREVERSIBLE — once deleted, the voice cannot be recovered and any saved voice_id referencing it will stop working. Confirm with the user before calling.
Fetch the detail of a single custom (cloned) voice by voice_id. Returns the voice's name and description. Use search_custom_voice to list custom voices and find a voice_id.
Retrieve recent TTS API usage history for the current API key. Returns a plain-text summary broken down by time period, showing the minutes used (and, when available, the voice and model) in each period. Takes no parameters — it reports usage over a recent default window. Use this to review how much synthesis has been consumed.
Retrieve recent usage for a single voice by voice_id. Returns a plain-text summary of the voice's per-day minutes used over a recent default window. Use search_voice or search_custom_voice to find a voice_id.
Merge two or more local audio files into a single file using ffmpeg. Supports plain concatenation, silence-gap insertion between clips (gap_ms), or crossfade blending (crossfade_ms). gap_ms and crossfade_ms are mutually exclusive. Output format is auto-detected from the inputs (all-same-ext -> that ext; mixed -> mp3) or overridden via output_format. Use this to stitch multiple text_to_speech outputs into one deliverable.
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.
More Other MCP servers
Awesome Mcp Servers
punkpeyeA collection of MCP servers.
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
ICSS
chokcoco不止于 CSS
ghidraMCP
LaurieWiredMCP Server for Ghidra
Unity MCP ✨
justinpbarnettUnity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Comments