Text to speech in about 190 voices and 31 languages: offline on your computer or via the cloud.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer sc_... API key from https://superclonica.com/speech-api (free: 3 minutes a day)
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
The API key's plan, the seconds of audio it allows per window and how many are left.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http superclonica-mcp https://superclonica.com/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer sc_... API key from https://superclonica.com/speech-api (free: 3 minutes a day)The API key's plan, the seconds of audio it allows per window and how many are left.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Search the voices this API key may use: stock voices F1-F5 (female) and M1-M5 (male), the key owner's own and bought voices, and every catalog voice (characters, narrators, announcers...). Matches names in any language, tags and descriptions. Each voice speaks all 31 languages; it sounds most natural in the language it was recorded in.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Words to search for, e.g. "darth vader", "calm female narrator", "anime girl". Leave out to list the stock and most liked voices. |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 100,
"description": "Words to search for, e.g. \"darth vader\", \"calm female narrator\", \"anime girl\". Leave out to list the stock and most liked voices."
}
},
"additionalProperties": false
}Turn a text into speech with one voice and return a link to the audio file (kept 1 h). The audio length counts against the key's plan. Up to 20000 characters per call; a long text takes longer, so voice long texts in parts.
| Argument | Type | Description |
|---|---|---|
| text* | string | The text to say. |
| voice* | string | A voice id from list_voices (32 characters), a stock voice (F1-F5, M1-M5) or a voice name, which must match one voice exactly. |
| format | string | |
| language* | string | The language of the text (ISO 639-1). |
| include_audio | boolean | Also return the audio itself inside the result (up to 3 MB), for clients that play audio. The link is always returned. |
{
"type": "object",
"required": [
"text",
"voice",
"language"
],
"properties": {
"text": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "The text to say."
},
"voice": {
"type": "string",
"maxLength": 100,
"minLength": 2,
"description": "A voice id from list_voices (32 characters), a stock voice (F1-F5, M1-M5) or a voice name, which must match one voice exactly."
},
"format": {
"enum": [
"mp3",
"wav",
"ogg"
],
"type": "string",
"default": "mp3"
},
"language": {
"enum": [
"ru",
"en",
"uk",
"de",
"es",
"fr",
"pt",
"ko",
"ar",
"bg",
"hr",
"cs",
"da",
"nl",
"et",
"fi",
"el",
"hi",
"hu",
"id",
"it",
"ja",
"lv",
"lt",
"pl",
"ro",
"sk",
"sl",
"sv",
"tr",
"vi"
],
"type": "string",
"description": "The language of the text (ISO 639-1)."
},
"include_audio": {
"type": "boolean",
"default": false,
"description": "Also return the audio itself inside the result (up to 3 MB), for clients that play audio. The link is always returned."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 1, 2026.