Audio

MiniMax Speech 2.8

MiniMax Speech 2.8 API is a production text to speech API for expressive voice generation, fast speech-turbo previews, higher-fidelity speech-hd output, preset voices, and reusable custom voice_id workflows.

Start creating API Docs

Text-to-speech API

speech-turbo + speech-hd

Preset or custom voice_id

MP3, WAV, PCM, FLAC

$0.06 / 1000 chars

MiniMax Speech 2.8 API text to speech demo cover

Start now

Create with MiniMax Speech 2.8

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-speech-2-8Create task

GEThttps://api.apixo.ai/api/v1/statusTask/minimax-speech-2-8?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

Speech quality mode.speech-turbo · speech-hd

voice_idrequired

Typetext

Use a documented MiniMax preset voice_id or a custom voice_id created by MiniMax Voice.

promptrequired

Typestring

Text to synthesize. Pause and expressive tags are supported when needed.

pronunciation_dictoptional

Typelist

Optional pronunciation overrides such as Omg/Oh my god.

speedoptional

Typeslider

Speaking speed from 0.5 to 2.0.

volumeoptional

Typeslider

Output volume from 0.1 to 10.0.

pitchoptional

Typeslider

Pitch adjustment from -12 to 12.

emotionoptional

Typeselect

Optional emotional tone.happy · sad · angry · fearful · disgusted · surprised · neutral

sample_rateoptional

Typeselect

Audio sample rate in Hz.8000 · 16000 · 22050 · 24000 · 32000 · 44100

bitrateoptional

Typeselect

Audio bitrate in bps.32000 · 64000 · 128000 · 256000

channeloptional

Typeselect

Mono or stereo output.mono · stereo

formatoptional

Typeselect

Output audio format.mp3 · wav · pcm · flac

language_boostoptional

Typeselect

Optional language hint for pronunciation and prosody.auto · English · Chinese · Chinese,Yue · Japanese · Korean · Spanish · French · German · Portuguese

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	Speech quality mode.speech-turbo · speech-hd
`voice_id`	text	required	Use a documented MiniMax preset voice_id or a custom voice_id created by MiniMax Voice.
`prompt`	string	required	Text to synthesize. Pause and expressive tags are supported when needed.
`pronunciation_dict`	list	optional	Optional pronunciation overrides such as Omg/Oh my god.
`speed`	slider	optional	Speaking speed from 0.5 to 2.0.
`volume`	slider	optional	Output volume from 0.1 to 10.0.
`pitch`	slider	optional	Pitch adjustment from -12 to 12.
`emotion`	select	optional	Optional emotional tone.happy · sad · angry · fearful · disgusted · surprised · neutral
`sample_rate`	select	optional	Audio sample rate in Hz.8000 · 16000 · 22050 · 24000 · 32000 · 44100
`bitrate`	select	optional	Audio bitrate in bps.32000 · 64000 · 128000 · 256000
`channel`	select	optional	Mono or stereo output.mono · stereo
`format`	select	optional	Output audio format.mp3 · wav · pcm · flac
`language_boost`	select	optional	Optional language hint for pronunciation and prosody.auto · English · Chinese · Chinese,Yue · Japanese · Korean · Spanish · French · German · Portuguese

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/minimax-speech-2-8" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "speech-turbo",
      "voice_id": "preset_english_043",
      "prompt": "Welcome to APIXO. Build a MiniMax Speech 2.8 API workflow for fast text to speech previews, product onboarding, and customer-facing voice experiences.",
      "speed": 1.02,
      "volume": 1,
      "pitch": 0,
      "emotion": "happy",
      "format": "mp3",
      "sample_rate": 24000,
      "bitrate": 128000,
      "channel": "stereo",
      "language_boost": "English"
    }
  }'

Full API documentation

MiniMax Speech 2.8 Tips

MiniMax Speech 2.8 API for Text to Speech and TTS Workflows

Generate expressive speech from text, compare MiniMax Speech 2.8 API turbo and HD pricing, and test preset or custom voice_id settings with real MP3 examples.

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 Speech 2.8 API Technical Specs

Integration-relevant limits and controls for MiniMax text-to-speech generation.

Modes

speech-turbo and speech-hd

Voice source

Preset voice_id or custom voice_id

Language boost

English, Chinese, Japanese, Korean, and more

Typical latency

5-30 seconds

Capabilities

Key MiniMax Speech 2.8 capabilities

MiniMax Speech 2.8 TTS API

Turn product copy, narration scripts, app messages, and dialogue into natural speech with a simple async API workflow.

Preset and custom voices

Start with common MiniMax preset voices, or pass a custom voice_id created by MiniMax Voice for branded narration.

Production voice controls

Tune speed, pitch, volume, emotion, sample rate, bitrate, channel, format, and language boost from the playground or API.

What can you build with MiniMax Speech 2.8?

AI voice agents and product narration

Use the MiniMax Speech 2.8 API as a text to speech API for assistants, onboarding flows, product tours, help centers, and customer-facing voice UX.

Audiobooks, podcasts, and creator content

Convert long-form scripts into expressive TTS API output while keeping voice, pace, and MP3/WAV delivery predictable for publishing workflows.

Localization and multilingual audio

Use language boost, MiniMax voice presets, and custom voice_id values to create localized speech API output for ads, lessons, explainers, and app content.

Read FAQ

MiniMax Speech 2.8 notes and questions

MiniMax Speech 2.8 requires mode, voice_id, and prompt in every request.

Prompt length is limited to 10000 characters after trimming whitespace.

Custom voice_id values must be valid for the current account and are normally created through MiniMax Voice first.

Actual latency varies by text length, selected quality mode, queue load, and route health.

Voice style depends on the selected preset voice_id or custom voice_id, so production apps should test each narrator before rollout.

Yes. Use MiniMax Voice to create a custom voice_id, then pass that voice_id to the MiniMax Speech 2.8 API for later text to speech generation.

APIXO

Create with MiniMax Speech 2.8

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

Start creating View API docs

MiniMax Speech 2.8

Create with MiniMax Speech 2.8

MiniMax Speech 2.8 API for Text to Speech and TTS Workflows

Start with an idea

Write an idea

Use an example

Adjust the look

Create

Keep results

Try again

MiniMax Speech 2.8 API Technical Specs

Modes

Voice source

Language boost

Typical latency

Key MiniMax Speech 2.8 capabilities

MiniMax Speech 2.8 TTS API

Preset and custom voices

Production voice controls

What can you build with MiniMax Speech 2.8?

AI voice agents and product narration

Audiobooks, podcasts, and creator content

Localization and multilingual audio

MiniMax Speech 2.8 notes and questions

Does MiniMax Speech 2.8 support custom voices?

What is the difference between speech-turbo and speech-hd?

Can I use MiniMax Speech 2.8 as a voice cloning API?

How is MiniMax Speech 2.8 priced on APIXO?

Create with MiniMax Speech 2.8