Remote text-to-speech MCP server with text_to_speech and list_voices tools. Free plan.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer <VoiceHue API key>. Create a free key at https://voicehue.com/dashboard#api-keys
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.
List the public VoiceHue voices a key can use: id, name, language and gender. Pass a voice id to text_to_speech.
Optional filter, for example en or zh. Matches the start of the language code.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http voicehue https://voicehue.com/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer <VoiceHue API key>. Create a free key at https://voicehue.com/dashboard#api-keysList the public VoiceHue voices a key can use: id, name, language and gender. Pass a voice id to text_to_speech.
| Argument | Type | Description |
|---|---|---|
| language | string | Optional filter, for example en or zh. Matches the start of the language code. |
{
"type": "object",
"properties": {
"language": {
"type": "string",
"description": "Optional filter, for example en or zh. Matches the start of the language code."
}
},
"additionalProperties": false
}Convert text to spoken audio with a VoiceHue voice. Returns the audio (MP3 by default, or WAV) and a one-line summary with the voice, number of characters and duration. Up to 1,200 characters per call. Use list_voices first to get a valid voice id.
| Argument | Type | Description |
|---|---|---|
| text* | string | The text to speak. |
| speed | number | Speaking speed, 0.5 to 2. |
| voice* | string | A voice id from list_voices. |
| format | string | Audio format. MP3 is the default. |
{
"type": "object",
"required": [
"text",
"voice"
],
"properties": {
"text": {
"type": "string",
"maxLength": 1200,
"minLength": 1,
"description": "The text to speak."
},
"speed": {
"type": "number",
"default": 1,
"maximum": 2,
"minimum": 0.5,
"description": "Speaking speed, 0.5 to 2."
},
"voice": {
"type": "string",
"description": "A voice id from list_voices."
},
"format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"default": "mp3",
"description": "Audio format. MP3 is the default."
}
},
"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 4, 2026.