MiniMax Speech 2.8 Turbo and HD
MiniMax Speech 2.8 comes in a low-latency Turbo tier for real-time agents and an HD tier producing studio-quality voiceovers for narration and podcasts.
- MiniMax
- 2 variants
- From $0.00006 per character
- Price
- See price
- Speed
- ~6s
- Best for
- Voice · Text to Voice
- Price
- See price
- Speed
- ~1s
- Best for
- Voice · Text to Voice
More from MiniMax.
A family groups the versions of one model line. Open one to compare its variants side by side.
Working with MiniMax Speech.
MiniMax Speech 2.8 splits by latency. Turbo is built for real-time agents, IVR and high-volume narration where response time decides the experience; HD produces studio-quality voiceovers with multiple voice options for narration, podcasts and accessibility content.
When to choose MiniMax Speech
Choose MiniMax Speech when the decision is between speed and studio quality within one voice family. Google's TTS is the pick for inline pacing tags, and Kling Voice for voices bound to Kling video.
Choosing between the variants
Turbo is the one for anything interactive — an agent answering in real time cannot wait for HD. HD is for recorded output where the listener will notice the difference in quality.
Questions about MiniMax Speech
The short answers. For anything specific to your setup, talk to our team.
Talk to an engineerPlan for your expected volume.Turbo. It is built for low-latency output in real-time agents and IVR, where a delay is more damaging than a small quality difference.
Yes, multiple voice options are available, which matters when narration and podcast content needs a consistent but distinct speaker.
For high-volume narration where cost and speed dominate, yes. For a flagship voiceover, HD is the tier that will hold up.