mcpField
S
Supertone TTS MCP

Supertone TTS MCP

Local
github.com/supertone-incMedia & Design0

About Supertone TTS MCP

MCP server for the Supertone TTS API. Generate natural speech, browse and preview

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"supertone": {
"command": "uvx",
"args": [
"supertone-mcp"
],
"env": {
"SUPERTONE_API_KEY": "<SUPERTONE_API_KEY>",
"SUPERTONE_MCP_VOICE_ID": "<SUPERTONE_MCP_VOICE_ID>",
"SUPERTONE_OUTPUT_DIR": "<SUPERTONE_OUTPUT_DIR>"
}
}
}
}
Run commanduvx supertone-mcp
Environment variables to set
SUPERTONE_API_KEYSecretSupertone API key
SUPERTONE_MCP_VOICE_IDDefault voice_id for synthesis (falls back to a preset voice)
SUPERTONE_OUTPUT_DIRDirectory where audio files are saved (default ~/supertone-tts-output/)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypisupertone-mcp0.3.1

Tools

14

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
autoplaybooleanNo
include_phonemesbooleanNoWhen true, request phoneme timing data alongside the audio (SDK 0.2.3). Defaults to false. Note: the phoneme data is not yet surfaced in the tool response — this is a pass-through flag for now.
languageanyNo
modelanyNo
normalized_textanyNoOptional pre-normalized text to use for synthesis (SDK 0.2.3). Only applies to the sona_speech_2 and sona_speech_2_flash models; other models ignore it. When omitted, the SDK default (None) is used.
output_formatanyNo
output_modeanyNo
pitch_shiftanyNo
speedanyNo
streamingbooleanNoWhen true, stream the audio via the chunked synthesize path instead of a single one-shot request. Streaming is ONLY supported by model=sona_speech_1; using streaming=true with any other model returns a validation error. Defaults to false (one-shot synthesize).
styleanyNo
textstringYes
voice_idanyNo

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.