👉 How to Choose a Speech Model?
Speech Model Selection
We’ve introduced a clear separation of speech models in the portal. You can choose from the following options:
MARS-8 (MARS8-PRO) – Latest model with improved quality
MARS-8 Instruction – Supports instruction-based generation
Mars-8-instruct gives you two ways to control expression:Embedded emotion tags - Add cues like
[happy],[sad], or sound effects like[laughing],[sighing]user_instructionsparameter - Provide broader tone guidance like “Speak in an excited, upbeat tone”
MARS-7 – Legacy model
How to select a model
Go to Project Settings.
Select your language (very important).
Open the Speech Model dropdown.
Select the model you want to use.
All new re-generations after this switch will be on current model(Selected Model).
ℹ️ Note:
Existing outputs remain unchanged, while any new regenerations will use the current model.
By default, the portal operates on the MARS8-PRO model, which is displayed as
Auto (Default).