Text-to-Speech - ImagineArt Help Center

Add your script directly or use the AI writer to help craft it. Text-to-Speech supports multiple languages and lets you fine-tune the output with the following settings.

Parameters

Parameter	Description
Speed	Controls how fast or slow the voice speaks.
Volume	Adjusts the loudness of the generated audio.
Pitch	Raises or lowers the tone of the voice.

Models

ElevenLabs v3

ElevenLabs’ latest generation model with highly expressive, natural-sounding speech and advanced emotional range.Expressive High Quality

MiniMax Speech 2.8 HD

MiniMax’s high-definition speech model delivering studio-quality audio with nuanced intonation and clarity.HD Audio Studio Quality

MiniMax Speech 2.8 Turbo

MiniMax’s fastest speech model optimized for low-latency generation without compromising on voice naturalness.Fast Low Latency

ElevenLabs v4

ElevenLabs’ highly expressive, natural-sounding speech and advanced emotional range.Expressive High Quality

ElevenLabs v4 turbo

ElevenLabs’ v4 turbo: cost-efficient, expressive, natural-sounding speech.Expressive High Quality

Emotions

Choose an emotion to shape how the voice delivers your script: Happy Sad Angry Fearful Disgusted Surprised Neutral

Voices

All voices support multiple languages.

Voice	Gender
Wise Woman	Female
Friendly Person	Non-binary
Deep Voice Man	Male
Calm Woman	Female
Casual Guy	Male
Lively Girl	Female
Patient Man	Male
Young Knight	Male
Determined Man	Male
Lovely Girl	Female
Decent Boy	Male
Imposing Manner	Male
Elegant Man	Male
Abbess	Female
Sweet Girl 2	Female
Exuberant Girl	Female

​Parameters

​Models