Audio model · MiniMax
MiniMax Speech 2.8 HD
Text-to-speech generation with MiniMax voices
What is MiniMax Speech 2.8 HD?
MiniMax Speech 2.8 HD generates spoken audio from your text. Choose a voice on an audio node and create narration or voiceovers for downstream video and avatar workflows.
Capabilities
- Generate speech from text
MiniMax Speech 2.8 HD on Melius
Melius runs MiniMax Speech 2.8 HD alongside every other major image, video, audio, and text model, so you can use it alongside other models in your workflow — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is MiniMax Speech 2.8 HD?
MiniMax Speech 2.8 HD generates spoken audio from your text. Choose a voice on an audio node and create narration or voiceovers for downstream video and avatar workflows.
How do I use MiniMax Speech 2.8 HD on Melius?
Melius is a node-based canvas: add a audio node, pick MiniMax Speech 2.8 HD from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.