Lifelike speech, two credits at a time.
MiniMax Speech 2.6 HD is a text-to-speech model with 17 preset voices, 7 emotion settings and support for your own cloned voices. On Zorq it shares a subscription with image, video and lipsync — write the line, voice it and put it in a video without switching tools.
Sign in with Google or Apple · No credit card to start · 25+ AI models
MiniMax Speech 2.6 HDWhy creators pick MiniMax Speech 2.6 HD
17 preset voices
Pick from 17 ready-made voices covering different tones and styles for narration, ads and characters.
7 emotion settings
Shift the same voice between 7 emotional deliveries to match the mood of your script.
Works with cloned voices
Voices you create with MiniMax Voice Clone appear here, so your scripts can be read in your own voice.
Flat 2 credits per generation
Every generation costs 2 credits — a predictable price for iterating on voiceovers.
How to use MiniMax Speech 2.6 HD on Zorq
No install, no waitlist — it runs in the browser.
Sign in free
Sign in with Google or Apple at zorqai.com — free starter credits, no credit card needed to start.
Open the voice studio
Go to /audio and open the text-to-speech tab, then select MiniMax Speech 2.6 HD.
Write and tune
Paste your script, pick one of 17 voices or your own cloned voice, and set one of 7 emotions.
Generate
Generate for 2 credits, listen, and download — or feed the audio into Zorq’s lipsync to make a face speak it.
Simple pricing that covers it all
Credit-based plans for image, video, voice and more — not just one media type.
Prices shown billed annually · save up to 67% vs monthly · compare all plans
Frequently asked questions
What is MiniMax Speech 2.6 HD?
MiniMax Speech 2.6 HD is a text-to-speech model on Zorq AI with 17 preset voices, 7 emotion settings and support for your own cloned voices. You type a script, pick a voice and emotion, and it generates natural spoken audio in the browser.
How many credits does MiniMax Speech 2.6 HD cost?
Each generation costs a flat 2 credits. That makes it easy to iterate on a voiceover — trying a different voice or emotion is always the same predictable price.
MiniMax Speech or ElevenLabs Eleven v3 — which should I use?
ElevenLabs Eleven v3 costs 4 credits per generation and delivers the most natural speech on Zorq, but it uses a fixed set of 20 voices. MiniMax Speech 2.6 HD is half the credits, adds 7 emotion settings, and is the only one of the two that works with your cloned voices.
Can it speak in my own voice?
Yes. Clone your voice first with MiniMax Voice Clone at /audio, and the saved voice becomes selectable in MiniMax Speech 2.6 HD for any script you write.
What can I do with the generated audio?
Download it for any project, or keep it inside Zorq: use it as the audio input for lipsync to create a talking video, or pair it with generated video and music — all in one subscription.
Try MiniMax Speech 2.6 HD now
One subscription covers this model plus 25+ more for image, video, voice and lipsync.