Skip to content
Model infoModelsSnapshot: 15 Oct 2026

MiniMax / Speech 02

MiniMax Speech 02 Turbo

Speed-oriented speech synthesis with audio streaming and voice controls.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
9 of 20 specification fields collected
Text input limit1,000,000 via file; 50,000 inline (async)See specification notes below
Languages24 languagesSee specification notes below
Input billingSee ratesMiniMax
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)

HTTP audio streaming and both WebSocket protocols are documented. Asynchronous synthesis returns a task instead.

Batch processing
Not collected

Long-form asynchronous synthesis is documented; that is not evidence of a separate Batch API.

Fine-tuning
Not collected

Voice cloning and voice design do not establish base-model fine-tuning support.

Knowledge cutoff
Not collected
Release date
2025-04-02Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
24 languagesSource for Languages (opens in a new tab)

The general synthesis guide lists 40, but the model-specific overview lists 24 for Speech 02.

Context caching
Not collected

Reusing a voice ID does not establish inference caching.

Maximum prompt characters
1,000,000 via file; 50,000 inline (async)Source for Maximum prompt characters (opens in a new tab)

Synchronous HTTP accepts fewer than 10,000 characters. Limits differ by transport.

Output formats
mp3, pcm, flac, wav, pcmu_raw, pcmu_wav, opusSource for Output formats (opens in a new tab)

Synchronous HTTP formats. Transport-specific formats may differ.

Audio sample rates
8000 Hz, 16000 Hz, 22050 Hz, 24000 Hz, 32000 Hz, 44100 HzSource for Audio sample rates (opens in a new tab)

G.711 μ-law uses 8 kHz; MP3 supports separate bitrate controls.

Voice controls
Speed, Volume, Pitch, Emotion, Pause markers, PronunciationSource for Voice controls (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

MiniMax

Provider source (opens in a new tab)
API model ID
speech-02-turbo
Access
Documented native API; an eligible account, API key and applicable balance or subscription are required. No paid inference was performed.
Regions
Default endpoint; api-uw.minimax.io is recommended for US West
API endpoint URL
POST https://api.minimax.io/v1/t2a_v2Source for API endpoint URL (opens in a new tab)
Regional endpoint
POST https://api-uw.minimax.io/v1/t2a_v2Source for Regional endpoint (opens in a new tab)

A latency recommendation, not a data-residency guarantee.

Maximum prompt characters
Fewer than 10,000 charactersSource for Maximum prompt characters (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis1$60.001M characters

Rate conditions

  1. Native pay-as-you-go character price. Voice design, cloning and preview generation may incur additional charges.
Pricing source (opens in a new tab)

Data & enterprise terms

The March 30, 2026 service terms retain provider IP and allow use of inputs and generated content to provide, maintain, develop and improve the service. This review does not establish a no-training or zero-retention guarantee.

Read the service policy (opens in a new tab)

MiniMax

Provider source (opens in a new tab)
API model ID
speech-02-turbo
Access
Documented native API; an eligible account, API key and applicable balance or subscription are required. No paid inference was performed.
Regions
Not collected
API endpoint URL
POST https://api.minimax.io/v1/t2a_async_v2Source for API endpoint URL (opens in a new tab)
Maximum prompt characters
50,000 inline; 1,000,000 in a txt/zip fileSource for Maximum prompt characters (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis1$60.001M characters

Rate conditions

  1. Native pay-as-you-go character price. Voice design, cloning and preview generation may incur additional charges.
Pricing source (opens in a new tab)

Data & enterprise terms

The March 30, 2026 service terms retain provider IP and allow use of inputs and generated content to provide, maintain, develop and improve the service. This review does not establish a no-training or zero-retention guarantee.

Read the service policy (opens in a new tab)

MiniMax

Provider source (opens in a new tab)
API model ID
speech-02-turbo
Access
Documented native API; an eligible account, API key and applicable balance or subscription are required. No paid inference was performed.
Regions
Default endpoint; api-uw.minimax.io is recommended for US West
API endpoint URL
wss://api.minimax.io/ws/v1/t2a_v2Source for API endpoint URL (opens in a new tab)
Regional endpoint
wss://api-uw.minimax.io/ws/v1/t2a_v2Source for Regional endpoint (opens in a new tab)

A latency recommendation, not a data-residency guarantee.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis1$60.001M characters

Rate conditions

  1. Native pay-as-you-go character price. Voice design, cloning and preview generation may incur additional charges.
Pricing source (opens in a new tab)

Data & enterprise terms

The March 30, 2026 service terms retain provider IP and allow use of inputs and generated content to provide, maintain, develop and improve the service. This review does not establish a no-training or zero-retention guarantee.

Read the service policy (opens in a new tab)

MiniMax

Provider source (opens in a new tab)
API model ID
speech-02-turbo
Access
Documented native API; an eligible account, API key and applicable balance or subscription are required. No paid inference was performed.
Regions
Default endpoint; api-uw.minimax.io is recommended for US West
API endpoint URL
wss://api.minimax.io/ws/v1/t2a_v2_bidiSource for API endpoint URL (opens in a new tab)
Regional endpoint
wss://api-uw.minimax.io/ws/v1/t2a_v2_bidiSource for Regional endpoint (opens in a new tab)

A latency recommendation, not a data-residency guarantee.

Maximum prompt characters
At most 10,000 per task_continue messageSource for Maximum prompt characters (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis1$60.001M characters

Rate conditions

  1. Native pay-as-you-go character price. Voice design, cloning and preview generation may incur additional charges.
Pricing source (opens in a new tab)

Data & enterprise terms

The March 30, 2026 service terms retain provider IP and allow use of inputs and generated content to provide, maintain, develop and improve the service. This review does not establish a no-training or zero-retention guarantee.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

MiniMax

speech-02-turbo
Not verified

No model-specific cache contract verified for this endpoint.

How it works
Not collected

No model-specific cache contract verified for this endpoint.

Minimum reusable input
Not collected

No model-specific cache contract verified for this endpoint.

Lifetime & refresh
Not collected

No model-specific cache contract verified for this endpoint.

How to enable it
Not collected

No model-specific cache contract verified for this endpoint.

Usage fields
Not collected

No model-specific cache contract verified for this endpoint.

Billing rules
Not collected

No model-specific cache contract verified for this endpoint.

Limits & data boundaries
Not collected

No model-specific cache contract verified for this endpoint.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

MiniMax

speech-02-turbo
Not verified

No model-specific cache contract verified for this endpoint.

How it works
Not collected

No model-specific cache contract verified for this endpoint.

Minimum reusable input
Not collected

No model-specific cache contract verified for this endpoint.

Lifetime & refresh
Not collected

No model-specific cache contract verified for this endpoint.

How to enable it
Not collected

No model-specific cache contract verified for this endpoint.

Usage fields
Not collected

No model-specific cache contract verified for this endpoint.

Billing rules
Not collected

No model-specific cache contract verified for this endpoint.

Limits & data boundaries
Not collected

No model-specific cache contract verified for this endpoint.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

MiniMax

speech-02-turbo
Not verified

No model-specific cache contract verified for this endpoint.

How it works
Not collected

No model-specific cache contract verified for this endpoint.

Minimum reusable input
Not collected

No model-specific cache contract verified for this endpoint.

Lifetime & refresh
Not collected

No model-specific cache contract verified for this endpoint.

How to enable it
Not collected

No model-specific cache contract verified for this endpoint.

Usage fields
Not collected

No model-specific cache contract verified for this endpoint.

Billing rules
Not collected

No model-specific cache contract verified for this endpoint.

Limits & data boundaries
Not collected

No model-specific cache contract verified for this endpoint.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

MiniMax

speech-02-turbo
Not verified

No model-specific cache contract verified for this endpoint.

How it works
Not collected

No model-specific cache contract verified for this endpoint.

Minimum reusable input
Not collected

No model-specific cache contract verified for this endpoint.

Lifetime & refresh
Not collected

No model-specific cache contract verified for this endpoint.

How to enable it
Not collected

No model-specific cache contract verified for this endpoint.

Usage fields
Not collected

No model-specific cache contract verified for this endpoint.

Billing rules
Not collected

No model-specific cache contract verified for this endpoint.

Limits & data boundaries
Not collected

No model-specific cache contract verified for this endpoint.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

332 voices

Choose a voice within MiniMax Speech 02 Turbo. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
Expressive NarratorEnglish_expressive_narratorEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Radiant GirlEnglish_radiant_girlEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Magnetic-voiced MaleEnglish_magnetic_voiced_manEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Compelling LadyEnglish_compelling_lady1EnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Aussie BlokeEnglish_Aussie_BlokeEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Captivating FemaleEnglish_captivating_female1EnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Upbeat WomanEnglish_Upbeat_WomanEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)
Trustworthy ManEnglish_Trustworth_ManEnglishPublished system voice; availability should be checked with the Get Voice API for the selected account and model.Voice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred closed-weight service variant: the exact model is documented through MiniMax service access and no corresponding weight release was identified in the reviewed official MiniMaxAI repository inventory. Service terms reserve underlying IP. Public M-series, H3 and Music 3 weights are explicitly excluded; the OpenAPI MIT label licenses documentation, not model weights.

Classification evidence (opens in a new tab)

Lifecycle dates

Released2 Apr 2025Source (opens in a new tab)

Sources reviewed