Voice Changer

Transform the voice in your audio files while preserving the original speech content and timing. Choose from a variety of high-quality voices with different characteristics, accents, and speaking styles.

Endpoint

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

Authentication

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

Request Parameters

Parameter	Type	Description	Required
`type`	string	Feature name: `VOICE_CHANGER`	✔️
`model`	string	Model name: `elevenlabs-voice-changer`	✔️
`conversationId`	string	Conversation identifier	✔️
`promptObject.audioUrl`	string	Path to the audio file to be voice changed	✔️
`promptObject.voice_id`	string	Target voice ID	✔️
`promptObject.output_format`	string	Audio output format	❌
`promptObject.model_id`	string	Speech-to-Speech model ID	❌
`promptObject.seed`	number	Seed for deterministic generation (0-4294967295)	❌
`promptObject.remove_background_noise`	boolean	Remove background noise from audio	❌

Voice Options (`voice_id`)

Voice ID	Name	Gender	Age	Accent	Description
`9BWtsMINqrJLrRacOk9x`	Aria	Female	Young	American	Expressive and warm
`CYw3kZ02Hs0563khs1Fj`	Roger	Male	Middle-aged	American	Confident and smooth
`EXAVITQu4vr4xnSDxMaL`	Sarah	Female	Young	American	Soft and pleasant
`FGY2WhTYpPnrIDTdsKH5`	Laura	Female	Middle-aged	American	Upbeat and lively
`IKne3meq5aSn9XLyUdCD`	Charlie	Male	Middle-aged	Australian	Casual and friendly
`JBFqnCBsd6RMkjVDRZzb`	George	Male	Middle-aged	British	Deep and authoritative
`LcfcDJNUP1GQjkzn1xUU`	Emily	Female	Young	American	Calm and clear
`N2lVS1w4EtoT3dr4eOWO`	Liam	Male	Young	American	Friendly and approachable
`XB0fDUnXU5powFXDhCwa`	Charlotte	Female	Young	Swedish	Seductive and alluring
`Xb7hH8MSUJpSbSDYk0k2`	Alice	Female	Middle-aged	British	Confident and versatile
`XrExE9yKIg1WjnnlVkGX`	Matilda	Female	Young	American	Warm and pleasant
`bIHbv24MWmeRgasZH58o`	Will	Male	Young	American	Friendly and enthusiastic
`cgSgspJ2msm6clMCkdW9`	Jessica	Female	Young	American	Expressive and lively
`D38z5RcWu1voky8WS1ja`	Eric	Male	Middle-aged	American	Friendly and approachable
`AZnzlk1XvdvUeBnXmlld`	Domi	Male	Young	American	Strong and confident
`ErXwobaYiN019PkySvjV`	Antoni	Male	Young	American	Well-rounded narrator
`VR6AewLTigWG4xSOukaG`	Arnold	Male	Middle-aged	American	Crisp and articulate
`pqHfZKP75CvOlQylNhV4`	Chris	Male	Middle-aged	American	Casual and conversational
`nPczCjzI2devNBz1zQrb`	Brian	Male	Middle-aged	American	Deep and authoritative
`onwK4e9ZLuTAKqWW03F9`	Daniel	Male	Young	British	Deep and authoritative
`ThT5KcBeYPX3keUQqHPh`	Lily	Female	Middle-aged	British	Warm and pleasant
`pFZP5JQG7iQjIQuC4Bku`	Bill	Male	Old	American	Strong and confident

Output Format Options (`output_format`)

Format	Sample Rate	Bitrate	Description
`mp3_44100_128`	44.1 kHz	128 kbps	Default - Good quality balance
`mp3_22050_32`	22.05 kHz	32 kbps	Lower quality, smaller file
`mp3_44100_192`	44.1 kHz	192 kbps	High quality
`mp3_44100_32`	44.1 kHz	32 kbps	Lower bitrate
`mp3_44100_64`	44.1 kHz	64 kbps	Medium quality
`mp3_44100_96`	44.1 kHz	96 kbps	Good quality

Speech-to-Speech Models (`model_id`)

Model ID	Description
`eleven_english_sts_v2`	Eleven English v2
`eleven_multilingual_sts_v2`	Eleven Multilingual v2

Interactive Example

API Playground

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

AI Model *

Audio File URL *

Target Voice *

Output Format

Speech-to-Speech Model

Seed (Optional)

Remove Background Noise

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_CHANGER",
  "model": "elevenlabs-voice-changer",
  "conversationId": "VOICE_CHANGER",
  "promptObject": {
    "audioUrl": "development/audios/sample-audio.wav",
    "voice_id": "9BWtsMINqrJLrRacOk9x",
    "output_format": "mp3_44100_128",
    "model_id": "eleven_english_sts_v2",
    "remove_background_noise": false
  }
}'

Response

The API returns a URL to the generated audio file with the transformed voice.

{}

Endpoint​

Authentication​

Request Parameters​

Voice Options (voice_id)​

Output Format Options (output_format)​

Speech-to-Speech Models (model_id)​

Interactive Example​