ElevenLabs Voice Design

Create custom AI voices from text descriptions using ElevenLabs' advanced AI voice design technology. Describe the voice characteristics you want, provide text to convert to speech, and receive high-quality audio output with a uniquely generated voice.

Supported Models

elevenlabs-voice-design: ElevenLabs Voice Design service

Parameters

Parameter	Type	Required	Description
`type`	string	Yes	Feature type, must be "VOICE_DESIGN"
`model`	string	Yes	Model identifier, use "elevenlabs-voice-design"
`promptObject.voice_description`	string	Yes	Text description of the voice characteristics you want to create
`promptObject.text`	string	Yes	Text to convert to speech using the designed voice
`promptObject.output_format`	string	No	Output audio format (default: "mp3_44100_128")
`promptObject.loudness`	number	No	Audio loudness level (0.0-1.0, default: 0.5)
`promptObject.guidance_scale`	number	No	How closely to follow the voice description (0.0-1.0, default: 0.5)

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	`<api-key>`
Content-Type	`application/json`

Supported Audio Formats

Output Formats

mp3_44100_128 - MP3, 44.1kHz, 128kbps (default)
mp3_44100_64 - MP3, 44.1kHz, 64kbps
mp3_44100_96 - MP3, 44.1kHz, 96kbps
mp3_44100_192 - MP3, 44.1kHz, 192kbps
mp3_22050_32 - MP3, 22.05kHz, 32kbps
pcm_16000 - PCM, 16kHz
pcm_22050 - PCM, 22.05kHz
pcm_24000 - PCM, 24kHz
pcm_44100 - PCM, 44.1kHz

Voice Description Guide

Effective Voice Descriptions

When describing voices, include these characteristics for best results:

Gender & Age

"A young female voice" / "An elderly male voice"
"A middle-aged woman" / "A teenage boy"

Tone & Personality

"Calm and soothing" / "Energetic and enthusiastic"
"Professional and authoritative" / "Warm and friendly"
"Mysterious and deep" / "Cheerful and upbeat"

Accent & Origin

"With a slight British accent" / "Southern American drawl"
"Neutral American accent" / "With a hint of Irish accent"

Voice Quality

"Deep and gravelly" / "Light and airy"
"Rich and resonant" / "Soft and whispered"
"Clear and articulate" / "Raspy and textured"

Example Descriptions

"A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent"
"A young, energetic female voice with a bright, cheerful tone and clear articulation"
"A professional, authoritative middle-aged male voice with a neutral accent"
"A warm, motherly female voice with a soft, soothing quality"

Parameters Explained

Loudness (0.0 - 1.0)

Controls the volume level of the generated audio:

Low (0.0-0.3): Quiet, subtle volume
Medium (0.4-0.7): Balanced, natural volume (recommended)
High (0.8-1.0): Loud, prominent volume

Guidance Scale (0.0 - 1.0)

Controls how closely the AI follows your voice description:

Low (0.0-0.3): More creative interpretation, less adherence to description
Medium (0.4-0.7): Balanced interpretation (recommended)
High (0.8-1.0): Strict adherence to description, less creative variation

Code Example

cURL
JavaScript
Python

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "VOICE_DESIGN",
"model": "elevenlabs-voice-design",
"promptObject": {
  "voice_description": "A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent",
  "text": "Howdy there, partner. Welcome to the wild west where anything can happen. I am the oldest one here!",
  "output_format": "mp3_44100_128",
  "loudness": 0.5,
  "guidance_scale": 0.5
}
}'

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'VOICE_DESIGN',
  model: 'elevenlabs-voice-design',
  promptObject: {
    voice_description: 'A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent',
    text: 'Howdy there, partner. Welcome to the wild west where anything can happen. I am the oldest one here!',
    output_format: 'mp3_44100_128',
    loudness: 0.5,
    guidance_scale: 0.5
  }
})
});

import requests

url = "https://api.1min.ai/api/features"
headers = {
  "Content-Type": "application/json",
  "API-KEY": "YOUR_API_KEY"
}

data = {
  "type": "VOICE_DESIGN",
  "model": "elevenlabs-voice-design",
  "promptObject": {
      "voice_description": "A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent",
      "text": "Howdy there, partner. Welcome to the wild west where anything can happen. I am the oldest one here!",
      "output_format": "mp3_44100_128",
      "loudness": 0.5,
      "guidance_scale": 0.5
  }
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

Try the API directly in your browser:

API Playground

https://api.1min.ai/api/features

AI Model *

Voice Description *

Detailed description of the voice characteristics you want to generate

Text to Speech *

The text that will be spoken in the designed voice

Output Format

Loudness (0.0-1.0)

Audio volume level - 0.0 for quiet, 1.0 for loud

Guidance Scale (0.0-1.0)

How closely to follow the voice description - higher values for stricter adherence

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "VOICE_DESIGN",
  "model": "elevenlabs-voice-design",
  "promptObject": {
    "voice_description": "A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent",
    "text": "Howdy there, partner. Welcome to the wild west where anything can happen — the land of dust, dreams, and danger. The sun blazes high above the desert plains, painting the horizon gold as tumbleweeds roll lazily by. In this place, courage is currency, and every man carves his own fate with grit and a six-shooter. Saloon doors creak, boots clatter on wooden floors, and the air smells of whiskey and gunpowder. Outlaws roam freely, sheriffs keep a wary eye, and fortune favors the bold. So saddle up, stranger — your story’s just beginning in this untamed frontier of endless possibility.",
    "output_format": "mp3_44100_128",
    "loudness": 0.5,
    "guidance_scale": 0.5
  }
}'

Response Format

The API returns multiple audio file paths (previews) that can be accessed via the Asset API:

{
  "aiRecord": {
    "uuid": "96af970c-0e7b-4f18-bf69-a56d84339112",
    "userId": "c937fbcc-fa8f-4565-a440-c4d87f56fcb2",
    "teamId": "a4e176b2-dabb-451e-9c58-62b451fa9630",
    "teamUser": {
      "teamId": "a4e176b2-dabb-451e-9c58-62b451fa9630",
      "userId": "c937fbcc-fa8f-4565-a440-c4d87f56fcb2",
      "userName": "John",
      "userAvatar": "https://lh3.googleusercontent.com/a/ACg8ocLqgsNsHRfmWF9d-E1RvJetVsEzxNOsOg-NXWNTpMxLDPJbwELI=s96-c",
      "status": "ACTIVE",
      "role": "ADMIN",
      "creditLimit": 100000000,
      "usedCredit": 576208,
      "createdAt": "2025-10-20T04:13:40.847Z",
      "createdBy": "SYSTEM",
      "updatedAt": "2025-10-21T10:47:50.537Z",
      "updatedBy": "SYSTEM"
    },
    "model": "elevenlabs-voice-design",
    "type": "VOICE_DESIGN",
    "metadata": null,
    "rating": null,
    "feedback": null,
    "conversationId": null,
    "status": "SUCCESS",
    "createdAt": "2025-10-21T10:48:51.978Z",
    "aiRecordDetail": {
      "promptObject": {
        "text": "Howdy there, partner. Welcome to the wild west where anything can happen — the land of dust, dreams, and danger. The sun blazes high above the desert plains, painting the horizon gold as tumbleweeds roll lazily by. In this place, courage is currency, and every man carves his own fate with grit and a six-shooter. Saloon doors creak, boots clatter on wooden floors, and the air smells of whiskey and gunpowder. Outlaws roam freely, sheriffs keep a wary eye, and fortune favors the bold. So saddle up, stranger — your story’s just beginning in this untamed frontier of endless possibility.",
        "loudness": 0.5,
        "output_format": "mp3_44100_128",
        "guidance_scale": 0.5,
        "voice_description": "A calm, tough and gruff old cowboy with a deep, gravelly, southern American accent"
      },
      "resultObject": [
        "development/audios/2025_10_21_17_49_04_791_124705_preview_1.mp3",
        "development/audios/2025_10_21_17_49_07_333_267627_preview_2.mp3",
        "development/audios/2025_10_21_17_49_08_452_450166_preview_3.mp3"
      ],
      "responseObject": {}
    },
    "additionalData": null,
    "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/audios/2025_10_21_17_49_04_791_124705_preview_1.mp3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIAVRUVQEFIHSKAXGE7%2F20251021%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20251021T104909Z&X-Amz-Expires=604800&X-Amz-Signature=4ca55283a218c16403e293672576163ff9739a8d06b589f62f3e0e6bdbaaf8bb&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject"
  }
}

Use Cases

Character Creation: Generate unique voices for game characters, animations, and storytelling
Content Creation: Create distinct narrator voices for audiobooks, podcasts, and videos
Prototype Development: Quickly test different voice styles for applications and products
Brand Voice Development: Explore voice characteristics for brand representation
Accessibility: Create voices that match specific user preferences or requirements
Education: Generate voices for educational content with specific personality traits
Marketing: Create memorable brand voices for advertisements and campaigns
Entertainment: Develop voices for virtual assistants, chatbots, and interactive experiences

Tips for Best Results

Be Descriptive: Include multiple characteristics (age, gender, accent, tone, quality)
Use Examples: Reference well-known voice types or personalities when applicable
Specify Accent: Include regional accents or linguistic characteristics
Describe Emotion: Mention the emotional tone or personality traits
Voice Quality: Include texture descriptions (smooth, raspy, deep, light)
Professional Terms: Use audio-related terms (resonant, gravelly, breathy, crisp)
Age Specification: Clearly define the perceived age of the voice
Guidance Scale: Start with 0.5 and adjust based on how closely you want to match the description
Loudness: Use 0.5 for natural volume, adjust based on your specific needs
Iterate: Try different descriptions to find the perfect voice for your needs

Error Handling

Common error scenarios and solutions:

Invalid voice_description: Ensure the description is clear and detailed
Text too long: Break long texts into smaller chunks for better processing
Invalid parameters: Check that loudness and guidance_scale are between 0.0 and 1.0
Generation failed: Try adjusting the voice description or guidance scale

Rate Limits

Voice design operations may have specific rate limits due to AI processing requirements
Consider the time needed for voice generation when planning bulk operations
Monitor your usage to avoid hitting concurrent processing limits

Supported Models​

Parameters​

Endpoint​

Request Headers​

Supported Audio Formats​

Output Formats​

Voice Description Guide​

Effective Voice Descriptions​

Example Descriptions​

Parameters Explained​

Loudness (0.0 - 1.0)​

Guidance Scale (0.0 - 1.0)​

Code Example​

Interactive Playground​