MiniMax Audio logo

MiniMax Audio

Text-to-speech tool (Speech 2.8) that clones a voice from a 10-second sample, creates new voices from a text description, and adds emotions like breaths, laughs and fillers like "um" into the speech.

Last verified: October 24, 2026
Alternative to: ElevenLabs
MiniMax Audio app screenshot

Short description

MiniMax Audio is the speech product of MiniMax, a Chinese AI company also known for its video models. It turns text into expressive speech that can include breaths, laughs and natural fillers like um. Creators use the web app at minimax.io/audio on monthly plans for cloned-voice content, and developers plug the API into chat, character and voice apps.

Features

  • Speech 2.8 HD and Turbo: HD for the highest quality, Turbo for cheaper and faster output. Launched January 23, 2026, alongside older 2.6 and 02 models.

  • 10-second voice cloning: Captures a voice's texture, breathiness and speaking pace from a short sample

  • Voice Design: Creates a new voice from a text description

  • Sound tags and fillers: Inline breath, laugh, chuckle and clear-throat sounds, plus natural um and uh fillers

  • Long-text jobs: An async API that handles up to 1M characters per request, for audiobook-scale work

  • 40+ languages: Per third-party hosts Together, Replicate and Cloudflare, though Replicate's HD page says 32. MiniMax's own page doesn't confirm a number.

  • Music 3.0 and Voice Isolator: Music generation and background-noise removal in the same Audio app

Pricing

  • How you pay: Pay-per-character API, or monthly plans for the web app that give you audio points

  • Starter: $5/mo

  • Standard: $30/mo, up to 100 custom voices

  • Pro: $99/mo, 1.1M points and up to 250 custom voices

  • Scale: $249/mo

  • Business: $999/mo

  • API: $60 per 1M characters for Turbo and $100 per 1M for HD, vs ElevenLabs' $40-80, so not cheaper

  • Cloning: $1.50 per cloned voice on the API

  • Voice Design: $3 per voice

Integrations

  • Platforms: Web app and a REST API with both instant and async text-to-speech. Cloud only, with closed model weights.

  • AI assistants and coding tools: Official MiniMax MCP server lets Claude Desktop, Cursor, Windsurf and OpenAI Agents generate speech, clone and design voices, and create images and video directly

  • Voice agent frameworks: LiveKit plugin (livekit-plugins-minimax-ai) and a Pipecat MiniMax TTS service let you use MiniMax voices in real-time agents

  • Third-party hosts: Also available through Replicate, Together AI and Cloudflare Workers AI

Platforms

  • Web app
  • REST API
❤️

What users love about MiniMax Audio

  • Cheap yearly cloning for creators: A YouTube creator who left ElevenLabs over cost pays under $330 a year for about 600k characters a month, with clone quality very good for the price

  • Accurate clones from little audio: A product team building a voice-clone feature picked MiniMax over the alternatives they tested because it copied voices closely from minimal input

  • Character voices that sound alive: Character-chat apps sound realistic in conversation, helped by inline breaths, laughs and um/uh fillers

😕

What users complain about MiniMax Audio

  • Easy to confuse with MiniMax's video model: When creators recommend MiniMax for voice, they often mean extracting the audio track from the H3 video model, so advice about MiniMax Audio is easy to misread

  • Less distinctive voices than Fish Audio: People who tried both rate them similarly but prefer Fish for having more interesting voices