Audio

MiniMax Voice

MiniMax Voice API creates reusable custom voices from a text description or one reference audio clip, covering voice design API and voice cloning API workflows for MiniMax Speech 2.8.

Start creating API Docs

Voice design API

Voice clone API

Reusable voice_id

MP3, M4A, WAV reference audio

$0.50 / request

MiniMax Voice API custom voice design demo cover

Start now

Create with MiniMax Voice

Loading workspace...

Authentication & Integration

Checking API access...

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

POSThttps://api.apixo.ai/api/v1/generateTask/minimax-voiceCreate task

GEThttps://api.apixo.ai/api/v1/statusTask/minimax-voice?taskId={taskId}Poll status

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

Parameters

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose the generation backend version.design · clone

voice_id_prefixrequired

Typetext

Prefix used by MiniMax to generate the final reusable voice_id. Use letters and digits, at least 6 characters, starting with a letter.

promptconditional

Typestring

Required in design mode. Describe accent, tone, age, pacing, and use case.Only in mode=design

preview_textconditional

Typestring

Text used to preview the created voice. Design mode is limited to 500 characters.

need_noise_reductionconditional

Typeboolean

Enable noise reduction for clone reference audio.Only in mode=clone

need_volume_normalizationconditional

Typeboolean

Normalize reference audio volume before cloning.Only in mode=clone

accuracyconditional

Typeslider

Optional clone accuracy control from 0 to 1.Only in mode=clone

language_boostconditional

Typeselect

Optional language hint for clone recognition.auto · English · Chinese · Chinese,Yue · Japanese · Korean · Spanish · French · GermanOnly in mode=clone

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose the generation backend version.design · clone
`voice_id_prefix`	text	required	Prefix used by MiniMax to generate the final reusable voice_id. Use letters and digits, at least 6 characters, starting with a letter.
`prompt`	string	conditional	Required in design mode. Describe accent, tone, age, pacing, and use case.Only in mode=design
`preview_text`	string	conditional	Text used to preview the created voice. Design mode is limited to 500 characters.
`need_noise_reduction`	boolean	conditional	Enable noise reduction for clone reference audio.Only in mode=clone
`need_volume_normalization`	boolean	conditional	Normalize reference audio volume before cloning.Only in mode=clone
`accuracy`	slider	conditional	Optional clone accuracy control from 0 to 1.Only in mode=clone
`language_boost`	select	conditional	Optional language hint for clone recognition.auto · English · Chinese · Chinese,Yue · Japanese · Korean · Spanish · French · GermanOnly in mode=clone

File parameters (URL arrays)

audio_urls[mode=clone]Required in clone mode. Upload one public MP3, M4A, or WAV reference audio file.Only in mode=clone

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/minimax-voice" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "design",
      "voice_id_prefix": "apixod72644139",
      "prompt": "A warm, confident product narrator voice for SaaS demos. Clear American English articulation, natural pacing, friendly energy, polished but not overly corporate.",
      "preview_text": "Welcome to APIXO. This MiniMax Voice API example designs a reusable custom voice for product narration and customer-facing audio."
    }
  }'

Full API documentation

MiniMax Voice Tips

MiniMax Voice API for Voice Cloning and Custom Voice Design

Create custom voices with MiniMax Voice API examples, compare design and clone workflows, preview generated audio, and prepare voice_id workflows for MiniMax Speech 2.8.

Create

Start with an idea

Pick a model, tune the settings, and create in one place.

Write an idea

Describe what you want to make.

Use an example

Start from a ready-made style.

Adjust the look

Tune the key settings quickly.

Create

Generate when everything feels right.

Keep results

Save what you want to revisit.

Try again

Make the next version faster.

MiniMax Voice API Technical Specs

Current request fields and workflow constraints for MiniMax custom voice creation.

Modes

design and clone

Clone input

Exactly 1 audio URL

Preview output

Reusable voice_id with preview audio

First poll

About 10 seconds after task creation

Capabilities

Key MiniMax Voice capabilities

Voice design from text

Describe the accent, tone, age, emotion, pace, and use case you want, then preview a generated custom voice.

Voice cloning from one clip

Upload one clean reference audio file and create a reusable voice_id for later text-to-speech synthesis.

Reusable voice workflow

Use the returned MiniMax voice_id with MiniMax Speech 2.8 to build branded narrators, agents, and content pipelines.

What can you build with MiniMax Voice?

Brand voice creation

Use the MiniMax Voice API as a custom voice API to create a consistent narrator for product videos, onboarding flows, ad creatives, and support experiences.

Voice cloning API workflows

Build controlled voice cloning API flows where users upload one authorized reference clip, preview the result, and reuse the generated custom voice workflow.

Voice libraries for apps

Generate reusable custom voice API assets for characters, tutors, podcast hosts, customer service agents, or internal training products.

Read FAQ

MiniMax Voice notes and questions

MiniMax Voice design mode requires voice_id_prefix, prompt, and preview_text.

MiniMax Voice clone mode requires exactly one publicly reachable reference audio URL.

voice_id_prefix must start with a letter, contain only letters or digits, and be at least 6 characters long.

A newly created custom voice that is never used later may become unavailable after 7 days.

Clone mode should only be used with audio you have permission to process and reproduce.

Yes. MiniMax Voice supports voice cloning API mode with exactly one reference audio URL, and it also supports voice design API mode for creating a voice from text description alone.

APIXO

Create with MiniMax Voice

Write a prompt, adjust the settings, and generate your next result in one place.

Start creating View API docs

MiniMax Voice

Create with MiniMax Voice

MiniMax Voice API for Voice Cloning and Custom Voice Design

Start with an idea

Write an idea

Use an example

Adjust the look

Create

Keep results

Try again

MiniMax Voice API Technical Specs

Modes

Clone input

Preview output

First poll

Key MiniMax Voice capabilities

Voice design from text

Voice cloning from one clip

Reusable voice workflow

What can you build with MiniMax Voice?

Brand voice creation

Voice cloning API workflows

Voice libraries for apps

MiniMax Voice notes and questions

Is MiniMax Voice a voice cloning API?

What do I do with the returned voice_id?

Can I send my own final voice_id?

What audio can I use with the MiniMax voice cloning API?

How is MiniMax Voice priced on APIXO?

Create with MiniMax Voice