Skip to main content
POST
/
clone-voice
curl -X POST https://api.magpipe.ai/functions/v1/clone-voice \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "name=Dr. Smith" \
  -F "description=Warm, professional male voice" \
  -F "files=@sample1.wav" \
  -F "files=@sample2.wav"

{
  "id": "pNInz6obpgDQGcFmaJgB",
  "name": "Dr. Smith",
  "description": "Warm, professional male voice",
  "preview_url": "https://api.elevenlabs.io/v1/voices/pNInz6obpgDQGcFmaJgB/preview.mp3",
  "provider": "elevenlabs",
  "created_at": "2024-01-15T10:30:00Z"
}
Create a professional voice clone using ElevenLabs technology. Upload audio samples of the voice you want to clone, and we’ll create a custom voice that can be used with your AI agents.

​
Request Body

Send as multipart/form-data:
​
name
string
required
Name for the cloned voice.Example: Dr. Smith
​
description
string
Description of the voice characteristics.Example: Warm, professional male voice
​
files
file[]
required
Audio files for voice cloning.Requirements:
  • At least 1 file, up to 25 files
  • Supported formats: WAV, MP3, M4A
  • At least 30 seconds of clean audio per file
  • Total audio should be 1-3 minutes for best results
  • Clear speech, minimal background noise

​
Response

​
id
string
Unique voice identifier (use as voice_id in agent config).
​
name
string
Voice display name.
​
description
string
Voice description.
​
preview_url
string
URL to preview the cloned voice.
​
provider
string
Voice provider (always elevenlabs for cloned voices).
curl -X POST https://api.magpipe.ai/functions/v1/clone-voice \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "name=Dr. Smith" \
  -F "description=Warm, professional male voice" \
  -F "files=@sample1.wav" \
  -F "files=@sample2.wav"

{
  "id": "pNInz6obpgDQGcFmaJgB",
  "name": "Dr. Smith",
  "description": "Warm, professional male voice",
  "preview_url": "https://api.elevenlabs.io/v1/voices/pNInz6obpgDQGcFmaJgB/preview.mp3",
  "provider": "elevenlabs",
  "created_at": "2024-01-15T10:30:00Z"
}

​
Voice Cloning Tips

For best results:
  1. Use high-quality recordings - Professional microphone, quiet room
  2. Provide diverse samples - Different sentences, natural intonation
  3. Avoid music/background noise - Clean speech only
  4. Include natural speech patterns - Not too formal or scripted
  5. 1-3 minutes total - More audio generally improves quality