voice_clone
Create a voice clone from provided audio files using ElevenLabs technology to replicate a specific voice for text-to-speech applications.
Instructions
Create an instant voice clone of a voice using provided audio files.
⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"name": "<name>",
"files": "<files>"
},
"name": "voice_clone"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| description | No | ||
| files | Yes | ||
| name | Yes |
Implementation Reference
- elevenlabs_mcp/server.py:451-465 (handler)The main handler function for the 'voice_clone' tool. It processes input files, calls the ElevenLabs API to create an instant voice clone (IVC), and returns success information including the new voice ID.
def voice_clone( name: str, files: list[str], description: str | None = None ) -> TextContent: input_files = [str(handle_input_file(file).absolute()) for file in files] voice = client.voices.ivc.create( name=name, description=description, files=input_files ) return TextContent( type="text", text=f"""Voice cloned successfully: Name: {voice.name} ID: {voice.voice_id} Category: {voice.category} Description: {voice.description or "N/A"}""", ) - elevenlabs_mcp/server.py:445-450 (registration)The @mcp.tool decorator registers the 'voice_clone' function as an MCP tool, including its description and parameters (name: str, files: list[str], description: str | None).
@mcp.tool( description="""Create an instant voice clone of a voice using provided audio files. ⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user. """ )