Home / Servers / ElevenLabs API / text_to_voice_design
Design A Voice.
An MCP tool from the ElevenLabs API server, hosted on mcp.hjlabs.in.
Design A Voice. Design a voice via a prompt. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create a voice use the… [POST /v1/text-to-voice/design]
Name on the gateway: elevenlabs_api__text_to_voice_design · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
output_format | string | Output format of the generated audio. Formatted as codec_sample_rate_bitrate.… |
voice_description required | string | Description to use for the created voice. |
model_id | eleven_multilingual_ttv_v2 | eleven_ttv_v3 | Model to use for the voice generation. Possible values… |
text | string | Text to generate, text length has to be between 100 and 1000. |
auto_generate_text | boolean | Whether to automatically generate a text suitable for the voice description. |
loudness | number | Controls the volume level of the generated voice. -1 is quietest, 1 is… |
seed | integer | Random number that controls the voice generation. Same seed with same inputs… |
guidance_scale | number | Controls how closely the AI follows the prompt. Lower numbers give the AI more… |
stream_previews | boolean | Determines whether the Text to Voice previews should be included in the… |
should_enhance | boolean | Whether to enhance the voice description using AI to add more detail and… |
remixing_session_id | string | The remixing session id. |
remixing_session_iteration_id | string | The id of the remixing session iteration where these generations should be… |
quality | number | Higher quality results in better voice output but less variety. |
reference_audio_base64 | string | Reference audio to use for the voice generation. The audio should be base64… |
prompt_strength | number | Controls the balance of prompt versus reference audio when generating voice… |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "elevenlabs_api__text_to_voice_design",
"arguments": {
"voice_description": "…"
}
}Or connect the ElevenLabs API server directly, which lists 487 tools including this one:
claude mcp add --transport http hj-elevenlabs-api https://mcp.hjlabs.in/mcp/elevenlabs-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the design a voice. tool with output_format set to ….