MiniMax · Tools

MiniMax Audio

Visit website

At a glance

Price
from 5 $/mo
Vendor
MiniMax

Specifications & properties

Key decision factors

Pricing model
Freemium 1
Audio functions
  • Text-to-speech
  • Voice cloning
  • Music generation
  • Audio enhancement
1

Pricing

Price from
5 $/mo 1
Free tier
Yes 1

Integration

API available
Yes 1

Quality

Voice cloning min. audio
10 sec 1
Report data / suggest a correction

Metrics vs. the category

Supported languages
n/a
Voice cloning min. audio
10 sec
Latency (real-time audio)
n/a

Audio suite from MiniMax with lifelike text to speech, music creation, voice design, instant voice cloning and a voice isolator. Points/credit-based: free points on login, audio API monthly subscriptions from $5.

Profile

MiniMax Audio is a text-to-speech and voice-cloning platform from MiniMax, the Shanghai-based AI company also known for its Hailuo video models and M-series LLMs. It targets creators, marketers and developers who need multilingual voiceovers or a cloned narrator voice, and it ships two ways: a consumer web app at minimax.io/audio with monthly subscriptions from $5, and a pay-per-character developer API on MiniMax's Open Platform. The current flagship model, Speech 2.8, focuses on natural, less robotic-sounding delivery.

Who builds it

MiniMax Group Inc. was founded in Shanghai in December 2021 by Yan Junjie, a former SenseTime computer-vision researcher, and listed on the Hong Kong Stock Exchange in January 2026. The workflow is the same on web and API: enter a script, pick one of 300+ pre-built voices or clone your own from a short sample, tune emotion, pitch and speed, then export. Developers reach the same engine via MiniMax's Open Platform using HTTP/WebSocket endpoints, an async endpoint for long text, and dedicated Voice Clone/Voice Design endpoints.

Core features

  • Speech 2.8 (January 23, 2026), the flagship model, adds "Native Sound Tags" that model natural fillers ("um," "uh") and breathing, plus improved cross-lingual handling that reduces accent bleed, starting with Mandarin-Japanese pairs.
  • Instant voice cloning from as little as 10 seconds of source audio (the API accepts 10 seconds to 5 minutes, plus an optional under-8-second sample for extra fidelity).
  • 300+ studio-quality pre-built voices spanning 50+ languages and accents, organized by gender, age, accent and style, with adjustable pitch, speed and emotion.
  • Speech 2.6 (October 2025), the prior flagship, targets voice agents with sub-250ms latency and automatic reading of URLs, emails, phone numbers, dates and money without manual preprocessing.
  • A developer API exposing synchronous HTTP/WebSocket TTS, an async endpoint for long documents, and separate Voice Clone/Voice Design endpoints billed independently from generation.
  • Tiered voice-library capacity: subscription plans include rising "voice slots" for storing cloned voices, from 10 on the entry plan up to 800 on the top published plan.

Pricing

  • Five Audio subscription tiers plus a custom option: Starter $5/month (100,000 audio points), Standard $30/month (300,000), Pro $99/month (1,100,000), Scale $249/month (3,300,000), and Business $999/month (20,000,000 points, 800 voice slots); Custom via sales.
  • Quarterly billing saves 10%, annual saves 20%, on every tier.
  • No permanent free plan is published; new visitors get a small number of free trial generations (MiniMax's voice generator page showed "5 free trials remaining" during our check) before a paid tier is required.
  • Separate pay-as-you-go API pricing: speech-2.8-turbo costs $60 per million characters, speech-2.8-hd costs $100 per million characters; cloning is billed per voice ($1.50 Rapid Voice Cloning, $3.00 Voice Design).
  • Always check MiniMax's current pricing page, since these tiers and rates have changed more than once in the past year.

Who it's for

Creators, marketers and indie developers needing occasional multilingual voiceovers or a one-off cloned voice will likely find the $5-30/month tiers enough once trial generations run out. Teams building voice agents, embedding TTS into a product, or needing large voice libraries and higher rate limits should look at Pro/Scale/Business or the pay-as-you-go API, which unlock more voice slots, higher rate limits and (on Business) priority access to new models.

Frequently asked questions

What does MiniMax Audio cost?

MiniMax Audio is billed through monthly "Audio" subscription tiers measured in audio points, separate from its pay-as-you-go developer API. The published tiers are Starter at $5/month (100,000 audio points), Standard at $30/month (300,000), Pro at $99/month (1,100,000), Scale at $249/month (3,300,000) and Business at $999/month (20,000,000 points, 800 voice slots), with a Custom tier available via sales; quarterly billing saves 10% and annual billing saves 20%. Developers calling the API directly instead pay per character: $60 per million characters on speech-2.8-turbo and $100 per million on speech-2.8-hd. Check the current pricing page before budgeting, since MiniMax has revised these tiers before.

Is MiniMax Audio free?

Not on an ongoing basis. MiniMax Audio gives new visitors a small number of free trial generations rather than a permanent free plan; MiniMax's own voice generator page showed a "5 free trials remaining" counter during our check. Once those trial generations are used, a paid subscription starting at $5/month (Starter, 100,000 audio points) is required to keep generating audio. MiniMax's Paid Service Terms confirm free accounts only get "basic features such as limited voice cloning functions and API service," with faster generation and more credits reserved for paid tiers. Check the live trial terms directly, as free allowances can change.

What languages and voices does MiniMax Audio support?

MiniMax Audio ships with 300+ studio-quality pre-built voices spanning 50+ languages and accents on its consumer voice-generator page, organized by gender, age, accent and speaking style. The underlying speech models are documented separately as supporting 40+ languages for generation and cross-lingual cloning, with the current Speech 2.8 model specifically working to reduce "accent bleed" between language pairs such as Mandarin and Japanese. Because the exact language count differs slightly by model generation (2.5, 2.6, 2.8), check MiniMax's model documentation for the figure tied to whichever model you plan to use.

Does MiniMax Audio support voice cloning?

Yes. MiniMax's voice cloning needs as little as 10 seconds of source audio to build a custom voice on the consumer app; the API is more flexible, accepting 10 seconds to 5 minutes of source audio plus an optional under-8-second sample for extra fidelity. The current Speech 2.8 model markets this as capturing "your unique texture, breathiness, and even your specific speaking pace" from that short sample, building on Speech 2.6's "Fluent LoRA" feature, which smooths cloned output even when the source recording has accents or disfluencies. On the API, cloning is billed separately from generation: $1.50 per Rapid Voice Clone and $3.00 per Voice Design call.

Does MiniMax Audio have an API, and can I use the audio commercially?

Yes, MiniMax exposes Audio through its Open Platform API: synchronous HTTP and WebSocket text-to-speech endpoints, an async endpoint for long-form text, and separate Voice Clone/Voice Design endpoints, all billed per character or per cloned voice rather than by subscription. That usage-based billing model is built for businesses embedding generated speech into their own products, which implies commercial use is expected for paying customers. That said, MiniMax does not publish one plain-language "you may resell this audio" clause on its pricing page; its Paid Service Terms only distinguish "basic" free features from fuller paid features. For commercially sensitive use (ads, resold audiobooks), read MiniMax's Audio Terms of Service and Paid Service Terms directly before relying on the output, since a specific plan-by-plan commercial license clause was not something we could confirm on the pages checked.

How does MiniMax Audio compare to ElevenLabs?

The two land at similar entry prices but differ on where the free tier lives: ElevenLabs has a genuine $0/month plan (10,000 credits), though it locks Instant Voice Cloning behind its $6/month Starter tier and up, while MiniMax Audio's cheapest paid tier is $5/month (100,000 audio points) but its "free" access is only a handful of trial generations, not an ongoing plan. On raw language reach, ElevenLabs' newest model (Eleven v3) claims 74 languages, versus MiniMax's 50+ languages/accents on its consumer voice library and 40+ for Speech 2.8's generation and cross-lingual cloning. Both support fast cloning from short samples (MiniMax: as little as 10 seconds; ElevenLabs: a comparably short Instant Voice Cloning sample) and both offer a metered developer API. Check both vendors' current pricing pages before committing, since both have changed tiers within the past year.